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

    Neuronpedia

    INDEX
    Explanations

    access

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bör
    -0.06
    calar
    -0.06
    ausal
    -0.06
     zijn
    -0.06
    dfa
    -0.06
    izzare
    -0.06
     такі
    -0.06
     Trung
    -0.06
    ensex
    -0.06
    Segoe
    -0.06
    POSITIVE LOGITS
     laws
    0.08
    /reg
    0.07
    /weather
    0.07
    폰
    0.07
    .serv
    0.06
     شور
    0.06
    {
↵
↵
    0.06
     wasting
    0.06
     quarters
    0.06
    ea
    0.06
    Act Density 0.006%

    No Known Activations