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

    Neuronpedia

    INDEX
    Explanations

    Bul

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ox
    -0.07
    _tw
    -0.07
    "All
    -0.07
     […]↵↵
    -0.06
    Reward
    -0.06
    .pop
    -0.06
     Biology
    -0.06
    %x
    -0.06
    ajs
    -0.06
    .nb
    -0.06
    POSITIVE LOGITS
     cô
    0.07
     Victims
    0.06
     CGRectMake
    0.06
    _Category
    0.06
    irket
    0.06
    τίου
    0.06
     họ
    0.06
     tě
    0.06
    (notification
    0.06
    &E
    0.06
    Act Density 0.004%

    No Known Activations