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

    Neuronpedia

    INDEX
    Explanations

    lob

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    —a
    -0.07
    _SERIAL
    -0.07
    oleans
    -0.07
    galement
    -0.07
     gamble
    -0.06
    díl
    -0.06
    Sentence
    -0.06
    America
    -0.06
    adas
    -0.06
    ‌آ
    -0.06
    POSITIVE LOGITS
     lob
    0.14
     Lob
    0.08
    lob
    0.07
     undone
    0.07
     количе
    0.07
     объ
    0.07
     Instrument
    0.06
    ber
    0.06
     Cottage
    0.06
     кус
    0.06
    Act Density 0.002%

    No Known Activations