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

    Neuronpedia

    INDEX
    Explanations

    bright colors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nominate
    -0.07
    药
    -0.07
    相信
    -0.07
     device
    -0.06
     bgcolor
    -0.06
    سد
    -0.06
    urve
    -0.06
     brunette
    -0.06
    stitute
    -0.06
    declare
    -0.06
    POSITIVE LOGITS
     clinging
    0.07
     Rencontre
    0.07
    Jun
    0.07
     sprawling
    0.06
    =""><
    0.06
     TOD
    0.06
     Mi
    0.06
    getElement
    0.06
    apo
    0.06
     MutableLiveData
    0.06
    Act Density 0.138%

    No Known Activations