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

    Neuronpedia

    INDEX
    Explanations

    politics and law

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     predicting
    -0.06
     pau
    -0.06
    .over
    -0.06
     <+
    -0.06
     depress
    -0.06
    女性
    -0.06
    اهر
    -0.06
    ■
    -0.06
     جور
    -0.06
     cramped
    -0.06
    POSITIVE LOGITS
    .Σ
    0.07
    _smart
    0.06
     Xã
    0.06
    ROM
    0.06
    als
    0.06
    organization
    0.06
    ture
    0.06
     silk
    0.06
    lis
    0.06
    nid
    0.06
    Act Density 0.000%

    No Known Activations