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

    Neuronpedia

    INDEX
    Explanations

    mobile

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _radio
    -0.07
    べて
    -0.07
     Volvo
    -0.07
    (clock
    -0.07
     глуб
    -0.07
    tones
    -0.07
    -з
    -0.06
     bowel
    -0.06
    soles
    -0.06
    폰
    -0.06
    POSITIVE LOGITS
    лика
    0.06
    combined
    0.06
     Brill
    0.06
     Penal
    0.06
    cession
    0.06
    妈
    0.06
    onents
    0.06
    andering
    0.06
     тим
    0.06
    feat
    0.06
    Act Density 0.024%

    No Known Activations