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

    Neuronpedia

    INDEX
    Explanations

    patients

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    效果
    -0.07
    atonin
    -0.07
     Transition
    -0.07
     hebben
    -0.06
    GPIO
    -0.06
    hos
    -0.06
     hysteria
    -0.06
    _windows
    -0.06
    られる
    -0.06
    っている
    -0.06
    POSITIVE LOGITS
     �
    0.07
     poder
    0.07
     Libert
    0.07
     nez
    0.07
     multip
    0.07
    _aspect
    0.06
    �
    0.06
     hone
    0.06
     sigmoid
    0.06
     impose
    0.06
    Act Density 0.037%

    No Known Activations