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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ราคา
    -0.07
    اتف
    -0.07
     Thu
    -0.07
     Kathleen
    -0.06
     Hyper
    -0.06
     　 　 　 　 　 　
    -0.06
     Wildcats
    -0.06
     Cold
    -0.06
    /***************************************************************************↵
    -0.06
    tier
    -0.06
    POSITIVE LOGITS
    /flutter
    0.07
     withdraw
    0.07
    (EX
    0.07
     soaked
    0.06
     grues
    0.06
     reuseIdentifier
    0.06
    =search
    0.06
     steering
    0.06
    Got
    0.06
    .ex
    0.06
    Act Density 0.692%

    No Known Activations