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

    Neuronpedia

    INDEX
    Explanations

    alt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Seats
    -0.08
     cavern
    -0.07
     jul
    -0.07
    تش
    -0.07
     BCH
    -0.07
     geen
    -0.06
    'url
    -0.06
    usterity
    -0.06
     perso
    -0.06
     Summers
    -0.06
    POSITIVE LOGITS
    _true
    0.06
    /dev
    0.06
    ART
    0.06
    hopefully
    0.06
     tránh
    0.06
     Rest
    0.06
     Finland
    0.06
    EXT
    0.05
    ILL
    0.05
    Preview
    0.05
    Act Density 0.002%

    No Known Activations