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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    anglicky
    -0.06
     Providers
    -0.06
     Spiritual
    -0.06
     Canton
    -0.06
    .frames
    -0.06
     Navigate
    -0.06
     Moderator
    -0.06
     Understand
    -0.06
     Apr
    -0.06
     bureauc
    -0.05
    POSITIVE LOGITS
    цій
    0.07
     hub
    0.07
    ヌ
    0.07
    strstr
    0.07
    _VOID
    0.07
    ции
    0.07
     роки
    0.06
    ụ
    0.06
    """.
    0.06
    (Qt
    0.06
    Act Density 0.000%

    No Known Activations