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

    Neuronpedia

    INDEX
    Explanations

    code calls

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     سل
    -0.08
    criteria
    -0.06
    olerance
    -0.06
     engagements
    -0.06
     Homer
    -0.06
     Params
    -0.06
     birlik
    -0.06
     Chand
    -0.06
    <TResult
    -0.06
    Notification
    -0.06
    POSITIVE LOGITS
    Orden
    0.06
    ='')↵
    0.06
    .Many
    0.06
    もしれない
    0.06
    -mort
    0.06
    キング
    0.06
    jj
    0.06
    ']!='
    0.06
     smugg
    0.06
    .ones
    0.06
    Act Density 0.096%

    No Known Activations