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

    Neuronpedia

    INDEX
    Explanations

    legal cases

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     drunk
    -0.06
    Jackson
    -0.06
     �
    -0.06
     ingl
    -0.06
     Thur
    -0.06
     hiring
    -0.06
     hitters
    -0.06
    ارية
    -0.06
    ante
    -0.06
    Profile
    -0.06
    POSITIVE LOGITS
     savun
    0.07
     Enhanced
    0.07
    sov
    0.07
    .Gen
    0.07
    �
    0.06
    .conn
    0.06
     apartheid
    0.06
    _RETRY
    0.06
    การส
    0.06
    BOT
    0.06
    Act Density 0.005%

    No Known Activations