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

    Neuronpedia

    INDEX
    Explanations

    latent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ꭼ
    -0.07
    麋
    -0.07
    =bool
    -0.07
    創新
    -0.07
    勇士
    -0.07
    _NULL
    -0.06
    征战
    -0.06
     thuyền
    -0.06
     fighting
    -0.06
    ティブ
    -0.06
    POSITIVE LOGITS
    QC
    0.07
    ,,,
    0.07
    ㉠
    0.07
     ju
    0.06
    idebar
    0.06
    sender
    0.06
     Hamas
    0.06
    Studio
    0.06
     estruct
    0.06
     jt
    0.06
    Act Density 0.002%

    No Known Activations