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

    Neuronpedia

    INDEX
    Explanations

    given

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    배
    -0.09
    urma
    -0.08
    ДЕ
    -0.07
    keyup
    -0.07
     EC
    -0.07
     keycode
    -0.07
    <_
    -0.07
     musique
    -0.07
    nerRadius
    -0.07
    ㎛
    -0.07
    POSITIVE LOGITS
    pro
    0.09
    /class
    0.07
     citations
    0.07
    ############
    0.07
     tir
    0.07
    仅仅
    0.07
     Optionally
    0.07
    #####
    0.06
    概念
    0.06
     monstrous
    0.06
    Act Density 0.006%

    No Known Activations