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

    Neuronpedia

    INDEX
    Explanations

    symbols and punctuation associated with code structures or formatting

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

    Code or configuration-related strings

    np_acts-logits-general · gemini-2.0-flash

    method calls or constructor calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     needed
    -1.06
     need
    -0.98
    needed
    -0.93
     Need
    -0.93
     Needed
    -0.91
    Need
    -0.87
    need
    -0.84
     NEED
    -0.81
    Needed
    -0.72
     cần
    -0.72
    POSITIVE LOGITS
    ValueStyle
    0.86
     виправивши
    0.73
     AssemblyProduct
    0.73
    ArgsConstructor
    0.71
    EndContext
    0.68
    StoryboardSegue
    0.68
    Jereo
    0.65
     tslint
    0.65
    AnimationsModule
    0.64
     Dummies
    0.64
    Act Density 0.082%

    No Known Activations