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

    Neuronpedia

    INDEX
    Explanations

    C*-algebras

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     brut
    -0.07
     바라
    -0.06
     gameplay
    -0.06
    _even
    -0.06
    -neutral
    -0.06
    externalActionCode
    -0.06
     Yao
    -0.06
    ovými
    -0.06
     analsex
    -0.06
    (co
    -0.06
    POSITIVE LOGITS
    .Adapter
    0.07
     Models
    0.07
     impeachment
    0.07
     розвиток
    0.06
     train
    0.06
     cls
    0.06
     downloaded
    0.06
     exhausting
    0.06
    enger
    0.06
    SizePolicy
    0.06
    Act Density 0.004%

    No Known Activations