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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DataExchange
    -0.07
    _heading
    -0.06
     میدان
    -0.06
    へ
    -0.06
     Speaking
    -0.06
     थ
    -0.06
    modified
    -0.06
    Personally
    -0.06
    νομα
    -0.06
    Mozilla
    -0.06
    POSITIVE LOGITS
     doe
    0.08
     Known
    0.07
     bru
    0.06
     sve
    0.06
     racks
    0.06
    (vo
    0.06
    @Json
    0.06
     FIX
    0.06
     BOOST
    0.06
    ±ط
    0.06
    Act Density 0.037%

    No Known Activations