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

    Neuronpedia

    INDEX
    Explanations

    snippets of articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    orders
    -0.06
    osals
    -0.06
    واع
    -0.06
     ['-
    -0.06
    ていない
    -0.06
    ají
    -0.06
    Specify
    -0.06
    _values
    -0.06
    ODEV
    -0.06
    children
    -0.06
    POSITIVE LOGITS
    0.07
     dragons
    0.06
    cipher
    0.06
    _mc
    0.06
     CERT
    0.06
    ruptions
    0.06
     civilizations
    0.06
     Eag
    0.06
     Aston
    0.06
     constructs
    0.06
    Act Density 0.216%

    No Known Activations