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

    Neuronpedia

    INDEX
    Explanations

    say "("

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Orth
    -0.08
    #ga
    -0.06
     appar
    -0.06
    billing
    -0.06
    Geo
    -0.06
    ůvod
    -0.06
     Century
    -0.06
     NSIndexPath
    -0.06
    DOCUMENT
    -0.06
     mapper
    -0.06
    POSITIVE LOGITS
    .Rec
    0.08
    につ
    0.07
     fila
    0.07
     mourn
    0.07
    .reset
    0.07
    akat
    0.07
     Blair
    0.07
    -fin
    0.06
    'e
    0.06
    _delta
    0.06
    Act Density 0.011%

    No Known Activations