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

    Neuronpedia

    INDEX
    Explanations

    id

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bass
    -0.08
     çı
    -0.07
     onset
    -0.07
    peł
    -0.07
    钻石
    -0.07
    children
    -0.07
    תברר
    -0.07
     soft
    -0.06
     Kö
    -0.06
    ive
    -0.06
    POSITIVE LOGITS
    _SUPPORTED
    0.08
    ACHINE
    0.07
    spath
    0.07
    覆
    0.07
    batis
    0.07
     spanish
    0.07
    ategories
    0.07
    luğun
    0.06
    램
    0.06
    imity
    0.06
    Act Density 0.000%

    No Known Activations