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

    Neuronpedia

    INDEX
    Explanations

    address changes, revisions, issues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _CUR
    -0.07
     hinge
    -0.06
    Than
    -0.06
     вог
    -0.06
     생성
    -0.06
     deserves
    -0.06
    (EX
    -0.06
    @store
    -0.06
    braco
    -0.06
     preset
    -0.06
    POSITIVE LOGITS
    里的
    0.07
    的人
    0.07
    联合
    0.06
     developments
    0.06
    [,]
    0.06
    -uppercase
    0.06
     unprecedented
    0.06
     specialists
    0.06
    初始化
    0.06
    Undo
    0.06
    Act Density 0.002%

    No Known Activations