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

    Neuronpedia

    INDEX
    Explanations

    Code/data snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cockpit
    -0.07
     ill
    -0.07
     implicated
    -0.06
    technical
    -0.06
    ynchronized
    -0.06
     aided
    -0.06
    Technical
    -0.06
     mastery
    -0.06
     お
    -0.06
     preds
    -0.06
    POSITIVE LOGITS
    Justin
    0.07
    ступ
    0.06
    .Gravity
    0.06
     Jason
    0.06
     �
    0.06
    MakeRange
    0.06
     Dien
    0.06
    otel
    0.06
    .Tags
    0.06
    競
    0.06
    Act Density 0.010%

    No Known Activations