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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to research findings and statistics

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

    Judge gun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.96
    WriteTagHelper
    -0.93
     سكانية
    -0.91
    parsedMessage
    -0.83
    SharedCtor
    -0.77
    ViewFeatures
    -0.76
     tartalomajánló
    -0.76
    entyfik
    -0.75
     <<<<<<<<<<<<<<
    -0.75
    oredCriteria
    -0.73
    POSITIVE LOGITS
     inoltre
    0.68
     autem
    0.60
     infatti
    0.53
     is
    0.51
     Marin
    0.50
    uset
    0.50
     enim
    0.47
    mrc
    0.47
    iconSize
    0.47
     however
    0.46
    Act Density 0.029%

    No Known Activations