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

    Neuronpedia

    INDEX
    Explanations

    attack/damage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     제목
    -0.07
    �
    -0.06
     Genetics
    -0.06
     Jal
    -0.06
    名字
    -0.06
    Ð
    -0.06
     drown
    -0.06
     умов
    -0.05
    α
    -0.05
     varargin
    -0.05
    POSITIVE LOGITS
    ----------------------------
    0.07
    !important
    0.07
    Tuesday
    0.06
    ........................
    0.06
     prayed
    0.06
    ---------------
    0.06
     unrecognized
    0.06
     XMLHttpRequest
    0.06
    ++);↵
    0.06
    Thirty
    0.06
    Act Density 0.020%

    No Known Activations