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

    Neuronpedia

    INDEX
    Explanations

    technical/research text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cultural
    -0.07
     Cultural
    -0.06
    .ErrorMessage
    -0.06
    Sem
    -0.06
     latina
    -0.06
    datatable
    -0.06
     �
    -0.06
    腕
    -0.06
    .valor
    -0.06
     dém
    -0.06
    POSITIVE LOGITS
     namespace
    0.07
    pii
    0.07
    endar
    0.07
    _MOV
    0.07
     κυ
    0.06
    teborg
    0.06
     ellipse
    0.06
    λύ
    0.06
     이런
    0.06
    627
    0.06
    Act Density 0.000%

    No Known Activations