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

    Neuronpedia

    INDEX
    Explanations

    regex

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cela
    -0.07
    .Comm
    -0.06
     dále
    -0.06
     паци
    -0.06
     كان
    -0.06
     villages
    -0.06
    munition
    -0.06
    Location
    -0.06
     Aus
    -0.06
    ilst
    -0.06
    POSITIVE LOGITS
     noticeably
    0.08
    ndern
    0.07
    .sql
    0.06
     Báo
    0.06
     꼭
    0.06
    ché
    0.06
    のだろう
    0.06
     vaping
    0.06
     Brain
    0.06
    (deg
    0.06
    Act Density 0.007%

    No Known Activations