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

    Neuronpedia

    INDEX
    Explanations

    https/http

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    מטוס
    -0.07
     Pompe
    -0.07
    �
    -0.07
    𫠊
    -0.07
     Justiça
    -0.07
    התנהג
    -0.07
    _ORIENTATION
    -0.07
     ActiveForm
    -0.07
    通过
    -0.06
    髭
    -0.06
    POSITIVE LOGITS
    Dual
    0.08
    !\
    0.07
    versed
    0.07
    환
    0.07
    Vac
    0.07
    HD
    0.07
     וא
    0.07
    라는
    0.07
    이라고
    0.07
    sı
    0.07
    Act Density 0.003%

    No Known Activations