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

    Neuronpedia

    INDEX
    Explanations

    _cookies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    'B
    -0.08
    escription
    -0.07
     MAV
    -0.07
     ZERO
    -0.07
     gib
    -0.07
     dwind
    -0.06
     Strict
    -0.06
    .ndarray
    -0.06
    recated
    -0.06
     DEN
    -0.06
    POSITIVE LOGITS
    ifications
    0.07
    itori
    0.06
    voj
    0.06
     trainable
    0.06
    velte
    0.06
    leştir
    0.06
     retirees
    0.06
    ReturnType
    0.06
     tým
    0.06
    temperature
    0.06
    Act Density 0.000%

    No Known Activations