Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mathematical relationships or equations involving physical parameters and their descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Mathematical/statistical notations

    np_acts-logits-general · gemini-2.0-flash

    introduces definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     виправивши
    -0.67
    енча
    -0.57
    AsUp
    -0.57
    MessageTagHelper
    -0.55
    WireFormatLite
    -0.55
    TagMode
    -0.55
    IndentedString
    -0.54
     ویکی‌پدیا
    -0.54
    oneofs
    -0.54
    sizeCache
    -0.53
    POSITIVE LOGITS
     denotes
    0.74
     denote
    0.64
     represents
    0.64
     represented
    0.54
     symbolizes
    0.53
     symbolized
    0.53
     signifies
    0.52
     rospy
    0.51
     denoted
    0.51
     bezeichnen
    0.51
    Act Density 0.919%

    No Known Activations