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

    Neuronpedia

    INDEX
    Explanations

    obox

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    symbol
    -0.06
    osg
    -0.06
     Страна
    -0.06
     predomin
    -0.06
     saúde
    -0.06
    kes
    -0.06
     نار
    -0.06
     '/../
    -0.06
    δια
    -0.06
     замен
    -0.05
    POSITIVE LOGITS
     utilize
    0.08
    _dash
    0.07
    essions
    0.07
     )(
    0.06
     estr
    0.06
    uds
    0.06
     relational
    0.06
    0.06
     thể
    0.06
    狀
    0.06
    Act Density 0.000%
    No Known Activations