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

    Neuronpedia

    INDEX
    Explanations

    syntax and structure in programming code

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

    Code, brackets, and semicolons

    np_acts-logits-general · gemini-2.0-flash

    code and punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DebuggerStep
    -0.71
    Portale
    -0.70
    Personendaten
    -0.64
     IFTT
    -0.63
     Wicidata
    -0.62
    TypedDataSet
    -0.61
     onCreateView
    -0.58
    AnimationsModule
    -0.57
    PYX
    -0.56
     invokingState
    -0.55
    POSITIVE LOGITS
    mangle
    0.55
    entera
    0.54
    ільки
    0.53
    konomi
    0.52
     umana
    0.51
     оригинала
    0.49
     pilotos
    0.48
     S
    0.47
    ]))
    0.47
    IComponent
    0.46
    Act Density 0.108%

    No Known Activations