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

    Neuronpedia

    INDEX
    Explanations

    programming keywords and constructs related to functions and data structures

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

    Code snippets or bracketed phrases

    np_acts-logits-general · gemini-2.0-flash

    programming-related keywords and natural language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    wing
    -0.50
    iling
    -0.46
     Wing
    -0.46
     wing
    -0.44
    vare
    -0.42
     tong
    -0.40
     Hutton
    -0.40
    Wing
    -0.40
    iled
    -0.39
     Pacific
    -0.39
    POSITIVE LOGITS
    
    0.62
    yntaxException
    0.61
    PerformLayout
    0.61
     ProtoMessage
    0.56
    ंदीखरीदारी
    0.50
    AndroidJUnit
    0.49
    rungsseite
    0.47
    msgTypes
    0.47
    TagMode
    0.46
     Signalez
    0.45
    Act Density 0.168%

    No Known Activations