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

    Neuronpedia

    INDEX
    Explanations

    foreign languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    buff
    -0.08
     Gordon
    -0.06
    يتي
    -0.06
    Assertions
    -0.06
     budget
    -0.06
    ifik
    -0.06
     Casino
    -0.06
     metre
    -0.06
     proceeded
    -0.06
    oader
    -0.06
    POSITIVE LOGITS
     участ
    0.28
     уча
    0.18
     υπο
    0.09
     участие
    0.08
     curso
    0.07
     ділян
    0.07
     участи
    0.07
    (parseInt
    0.07
    ...</
    0.07
    (actor
    0.07
    Act Density 0.001%

    No Known Activations