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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =obj
    -0.08
    制定
    -0.07
    _READONLY
    -0.07
     Kun
    -0.07
     boon
    -0.07
    ≦
    -0.07
    ✤
    -0.07
    图
    -0.07
    镘
    -0.06
    公用
    -0.06
    POSITIVE LOGITS
    PLAY
    0.07
    .Server
    0.07
    به
    0.07
    ysical
    0.07
    칠
    0.07
    じ
    0.06
    _form
    0.06
    chers
    0.06
    _ERRORS
    0.06
    avi
    0.06
    Act Density 0.068%

    No Known Activations