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

    Neuronpedia

    INDEX
    Explanations

    comparisons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sep
    -0.07
    stack
    -0.07
    tgt
    -0.06
    archical
    -0.06
    csr
    -0.06
    .Compute
    -0.06
    $
↵
    -0.06
     Ма
    -0.06
    وغ
    -0.06
    .floor
    -0.06
    POSITIVE LOGITS
     ogl
    0.07
     begged
    0.07
     педагог
    0.06
     rodin
    0.06
    ，”
    0.06
    ？”
    0.06
     Ris
    0.06
     предвар
    0.06
     Scalia
    0.06
     القي
    0.06
    Act Density 0.024%

    No Known Activations