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

    Neuronpedia

    INDEX
    Explanations

    man

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ibling
    -0.06
    /c
    -0.06
    ]:
    -0.06
    At
    -0.06
     headers
    -0.06
    xs
    -0.06
    _readable
    -0.06
     laughing
    -0.06
    stants
    -0.06
    imulator
    -0.06
    POSITIVE LOGITS
     прин
    0.07
    论
    0.07
     mischief
    0.07
    AndFeel
    0.07
    _MESSAGE
    0.07
    toArray
    0.06
    Modern
    0.06
     önüne
    0.06
     fishes
    0.06
     há
    0.06
    Act Density 0.001%

    No Known Activations