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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and sentence endings

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

    Code, filenames, or angle brackets

    np_acts-logits-general · gemini-2.0-flash

    technical documentation and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Catatan
    -0.60
     SALUD
    -0.55
     bien
    -0.54
    ,
    -0.53
    Zdroj
    -0.49
     haut
    -0.49
     Pág
    -0.49
    Comentários
    -0.48
     CHAPITRE
    -0.48
     a
    -0.47
    POSITIVE LOGITS
    TypedDataSet
    0.92
    ⓧ
    0.90
    enderror
    0.87
    numerusform
    0.86
     Shakspeare
    0.84
     Cæsar
    0.84
     Signalez
    0.83
    TestingModule
    0.82
    ftagPool
    0.82
    WebVitals
    0.81
    Act Density 0.100%

    No Known Activations