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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     boxes
    -0.06
     SharedPreferences
    -0.06
     Numero
    -0.06
     परम
    -0.06
     التاريخ
    -0.06
     đổ
    -0.06
     Images
    -0.06
     prosecute
    -0.06
     UNICODE
    -0.06
     World
    -0.06
    POSITIVE LOGITS
    太阳城
    0.06
    _MT
    0.06
     $↵↵
    0.06
    び
    0.06
    Λ
    0.06
    ...↵↵↵↵↵↵
    0.06
     л
    0.06
    !!!↵↵
    0.06
    .↵↵↵↵↵↵↵↵
    0.06
    kl
    0.06
    Act Density 0.027%

    No Known Activations