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

    Neuronpedia

    INDEX
    Explanations

    Binning data into classes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Children
    -0.07
    쵥
    -0.07
     He
    -0.07
    别墅
    -0.07
     홈페이지
    -0.06
    俚
    -0.06
    맆
    -0.06
    OnInit
    -0.06
    po
    -0.06
     sizeof
    -0.06
    POSITIVE LOGITS
    lıkl
    0.07
    ql
    0.07
     Eating
    0.07
     dalam
    0.07
    -query
    0.07
    etyl
    0.07
    -ap
    0.07
    �
    0.07
     materiał
    0.07
    行动
    0.07
    Act Density 0.013%

    No Known Activations