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

    Neuronpedia

    INDEX
    Explanations

    github

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cms
    -0.08
     Platforms
    -0.07
    avi
    -0.07
    _variance
    -0.07
    ToBounds
    -0.06
     SendMessage
    -0.06
    APO
    -0.06
     />
↵
    -0.06
     SF
    -0.06
     Deaths
    -0.06
    POSITIVE LOGITS
     neu
    0.07
    осудар
    0.06
    igail
    0.06
     cong
    0.06
     좋
    0.06
     dah
    0.06
     developmental
    0.06
    liqu
    0.06
    (dAtA
    0.06
    _worker
    0.06
    Act Density 0.003%

    No Known Activations