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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ोजन
    -0.07
    /tos
    -0.06
    .Configuration
    -0.06
    ited
    -0.06
    δικ
    -0.06
     yg
    -0.06
     ((((
    -0.06
    不可
    -0.06
    aining
    -0.06
     الخط
    -0.06
    POSITIVE LOGITS
     Redskins
    0.07
     політики
    0.07
     complet
    0.07
    Enable
    0.07
    .references
    0.06
    Align
    0.06
     climate
    0.06
     appropri
    0.06
     Senator
    0.06
    wp
    0.06
    Act Density 0.002%

    No Known Activations