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

    Neuronpedia

    INDEX
    Explanations

    H

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _RC
    -0.08
     Mis
    -0.07
     further
    -0.07
     weiter
    -0.07
    ຣ
    -0.07
    莳
    -0.07
    _detect
    -0.07
     subdivisions
    -0.07
     Arrays
    -0.07
     Rodr
    -0.06
    POSITIVE LOGITS
    Optimizer
    0.07
    字母
    0.07
    iação
    0.07
    poly
    0.07
    تقييم
    0.07
    جم
    0.07
     percent
    0.07
     групп
    0.07
    kor
    0.07
     Aj
    0.07
    Act Density 0.003%

    No Known Activations