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

    Neuronpedia

    INDEX
    Explanations

    code/database queries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    肚子
    -0.07
     Less
    -0.07
     sigh
    -0.07
    bursement
    -0.06
    透露
    -0.06
    Wonder
    -0.06
    Ԏ
    -0.06
     dub
    -0.06
    струк
    -0.06
    -clear
    -0.06
    POSITIVE LOGITS
    ulators
    0.08
    vements
    0.07
     האחרונה
    0.07
     vertices
    0.07
    engeance
    0.07
     arrived
    0.07
    replaceAll
    0.07
     controllers
    0.07
    	Method
    0.07
    是一个
    0.07
    Act Density 0.006%

    No Known Activations