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

    Neuronpedia

    INDEX
    Explanations

    financial/legal troubles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	trans
    -0.06
     Hart
    -0.06
    ocrates
    -0.06
     Soviet
    -0.06
    .Pending
    -0.06
    .Light
    -0.06
     Zh
    -0.06
     任
    -0.06
     mínimo
    -0.06
     Hive
    -0.06
    POSITIVE LOGITS
    -carousel
    0.07
    ulmuş
    0.07
     كه
    0.07
     caract
    0.07
     dél
    0.06
     Qin
    0.06
    šlo
    0.06
    333
    0.06
     quả
    0.06
    ’int
    0.06
    Act Density 0.113%

    No Known Activations