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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hen
    -0.07
    _BIG
    -0.07
    -width
    -0.07
     SMALL
    -0.07
    .ALL
    -0.07
    Af
    -0.07
     getY
    -0.07
     medium
    -0.07
    Long
    -0.06
     User
    -0.06
    POSITIVE LOGITS
    hh
    0.06
    явление
    0.06
     Joker
    0.06
    gap
    0.06
     facet
    0.06
    百科
    0.06
     lacking
    0.06
    points
    0.06
    眼下
    0.06
    esses
    0.06
    Act Density 0.043%

    No Known Activations