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

    Neuronpedia

    INDEX
    Explanations

    Elevated

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _pkg
    -0.07
     pkg
    -0.06
    ㏃
    -0.06
    뻬
    -0.06
    _cmd
    -0.06
     hindsight
    -0.06
     Actors
    -0.06
     lucky
    -0.06
    素
    -0.06
     atual
    -0.06
    POSITIVE LOGITS
    站长
    0.07
     yatırım
    0.07
    wiąz
    0.07
    鳊
    0.07
    魔法师
    0.07
    弹性
    0.07
    出色的
    0.07
    izona
    0.07
    Variant
    0.07
    uous
    0.07
    Act Density 0.062%

    No Known Activations