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

    Neuronpedia

    INDEX
    Explanations

    technical code elements, specifically related to JavaScript libraries and frameworks

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

    Text after the number zero

    np_acts-logits-general · gemini-2.0-flash

    descriptive phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.48
    Conteúdo
    -0.45
     chiusura
    -0.44
     bedo
    -0.43
     in
    -0.41
     that
    -0.40
     meant
    -0.39
     étan
    -0.39
     extended
    -0.39
     corretamente
    -0.38
    POSITIVE LOGITS
    rxjs
    1.05
     يتيمه
    0.96
     GenerationType
    0.92
    AnchorStyles
    0.89
    principalColumn
    0.84
    '],
    0.83
    出版年
    0.82
    zzleHttp
    0.81
    `,
    0.80
    Hochspringen
    0.78
    Act Density 0.038%

    No Known Activations