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

    Neuronpedia

    INDEX
    Explanations

    Council

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     вс
    -0.07
    req
    -0.07
    elerden
    -0.06
    ！」↵↵
    -0.06
    {
↵
↵
    -0.06
     humanoid
    -0.06
    щество
    -0.06
    pron
    -0.06
    ondheim
    -0.06
    $pdf
    -0.06
    POSITIVE LOGITS
     offsetof
    0.06
    Front
    0.06
    że
    0.06
    Double
    0.06
     oracle
    0.06
    cdf
    0.06
     Manufacturing
    0.06
     each
    0.06
    Clark
    0.06
    (count
    0.06
    Act Density 0.001%

    No Known Activations