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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    组
    -0.08
    mind
    -0.07
     학교
    -0.07
     कट
    -0.07
    okus
    -0.06
     Кал
    -0.06
    จะเป
    -0.06
    組
    -0.06
     moderated
    -0.06
     техні
    -0.06
    POSITIVE LOGITS
    求
    0.06
    isFunction
    0.06
     พล
    0.06
    imesteps
    0.06
     LIB
    0.06
    ////////////
    0.06
     poorer
    0.06
    essel
    0.06
    /**↵
    0.06
     кл
    0.06
    Act Density 0.001%

    No Known Activations