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

    Neuronpedia

    INDEX
    Explanations

    biodistribution

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    也不敢
    -0.07
    fr
    -0.07
    _ENTRY
    -0.06
     risk
    -0.06
    合伙
    -0.06
    serious
    -0.06
    веч
    -0.06
    岢
    -0.06
    ヒ
    -0.06
    _BUTTON
    -0.06
    POSITIVE LOGITS
     Nx
    0.07
    舣
    0.07
     portrayal
    0.07
    stars
    0.07
    骓
    0.07
    olume
    0.07
    _LOAD
    0.07
    ограм
    0.06
    Few
    0.06
     Theatre
    0.06
    Act Density 0.023%

    No Known Activations