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

    Neuronpedia

    INDEX
    Explanations

    choice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ön
    -0.08
    erra
    -0.08
    ungan
    -0.06
    ño
    -0.06
     prefix
    -0.06
    erte
    -0.06
    clear
    -0.06
     payment
    -0.06
    bersome
    -0.06
    urious
    -0.06
    POSITIVE LOGITS
    /A
    0.07
    ftp
    0.07
    (TYPE
    0.07
    (arc
    0.07
     вар
    0.07
    Europe
    0.06
    intval
    0.06
    .table
    0.06
     interle
    0.06
     existence
    0.06
    Act Density 0.009%

    No Known Activations