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

    Neuronpedia

    INDEX
    Explanations

    medical research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     guesses
    -0.07
     Napoleon
    -0.07
    xcc
    -0.07
    -components
    -0.07
    /cache
    -0.07
    项
    -0.07
     바랍니다
    -0.07
    된
    -0.06
    orb
    -0.06
    vw
    -0.06
    POSITIVE LOGITS
    _legacy
    0.06
    .github
    0.06
    omitempty
    0.06
    Hair
    0.06
     intercourse
    0.06
     asym
    0.06
     warfare
    0.06
    _experiment
    0.06
    bara
    0.06
    :]↵↵
    0.05
    Act Density 0.034%

    No Known Activations