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

    Neuronpedia

    INDEX
    Explanations

    spanish pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Disposable
    -0.07
     tung
    -0.07
    FOR
    -0.07
    泰
    -0.06
     balloon
    -0.06
    timeline
    -0.06
    acoes
    -0.06
    ERGY
    -0.06
    _CLEAR
    -0.06
    atives
    -0.06
    POSITIVE LOGITS
     lenses
    0.07
    曼
    0.06
     bouts
    0.06
     gücü
    0.06
    таки
    0.06
     jouer
    0.06
    .beta
    0.06
     programme
    0.06
     розвиток
    0.06
    ιος
    0.06
    Act Density 0.004%

    No Known Activations