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

    Neuronpedia

    INDEX
    Explanations

    function

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    お話
    -0.07
    茁
    -0.07
     investing
    -0.07
    病例
    -0.07
    lest
    -0.07
    .control
    -0.06
    邮寄
    -0.06
    _ALIAS
    -0.06
    _except
    -0.06
     adult
    -0.06
    POSITIVE LOGITS
    疗效
    0.07
     HW
    0.07
     is
    0.07
     cumulative
    0.06
    sx
    0.06
     creek
    0.06
     hence
    0.06
    xa
    0.06
     espera
    0.06
     sig
    0.06
    Act Density 0.001%

    No Known Activations