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

    Neuronpedia

    INDEX
    Explanations

    deadline

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    نش
    -0.07
     presence
    -0.07
    xac
    -0.07
    也曾
    -0.06
    .setX
    -0.06
    affected
    -0.06
    ₌
    -0.06
     herein
    -0.06
    人群中
    -0.06
    游戏当中
    -0.06
    POSITIVE LOGITS
    䥽
    0.07
    텨
    0.07
     smoothing
    0.07
    /Graphics
    0.07
    航班
    0.07
     Geile
    0.06
     Kat
    0.06
    ammers
    0.06
    arf
    0.06
     vag
    0.06
    Act Density 0.004%

    No Known Activations