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

    Neuronpedia

    INDEX
    Explanations

    game theory/math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    amer
    -0.08
     axis
    -0.08
    axis
    -0.08
     Moc
    -0.07
    Issuer
    -0.07
     oči
    -0.07
    amm
    -0.07
    apte
    -0.07
     tanker
    -0.07
    .Row
    -0.07
    POSITIVE LOGITS
    ��
    0.08
    ্দেশ
    0.08
     Models
    0.08
     Eval
    0.08
     يونيو
    0.08
    0.08
    јед
    0.08
    -ħ
    0.08
    ------------------------------------------------------------------------
    0.08
     pogosto
    0.08
    Act Density 0.011%
    No Known Activations