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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    水库
    -0.07
     gloss
    -0.07
    硙
    -0.07
     germ
    -0.07
    _flat
    -0.07
     elk
    -0.07
     muc
    -0.07
    翻开
    -0.07
     dedicate
    -0.07
    输卵
    -0.07
    POSITIVE LOGITS
     rekl
    0.07
    //
↵
    0.07
    COMP
    0.07
    //↵
    0.07
    ㏂
    0.06
    ﻌ
    0.06
    oppins
    0.06
    _ENDPOINT
    0.06
     predictions
    0.06
    ῶ
    0.06
    Act Density 0.001%

    No Known Activations