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

    Neuronpedia

    INDEX
    Explanations

    over

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    엨
    -0.07
    (LOG
    -0.07
    _pressure
    -0.06
     KP
    -0.06
    ǰ
    -0.06
    墼
    -0.06
     hưởng
    -0.06
     forensic
    -0.06
    렧
    -0.06
    wię
    -0.06
    POSITIVE LOGITS
    handler
    0.07
    Clickable
    0.07
     acted
    0.07
    encoded
    0.06
    挂牌
    0.06
    发言人
    0.06
    .Business
    0.06
     Ay
    0.06
     Garc
    0.06
     banner
    0.06
    Act Density 0.014%

    No Known Activations