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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stron
    -0.08
    .attrs
    -0.07
     Sb
    -0.07
     subur
    -0.06
    .opensource
    -0.06
     purse
    -0.06
     HttpStatus
    -0.06
     sar
    -0.06
     національ
    -0.06
     Пов
    -0.06
    POSITIVE LOGITS
    echo
    0.07
    chan
    0.07
    ernen
    0.06
    852
    0.06
    osition
    0.06
     कहत
    0.06
    象
    0.06
    861
    0.06
    ват
    0.06
    =X
    0.06
    Act Density 0.002%

    No Known Activations