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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nø
    -0.07
     malzem
    -0.07
    urrenc
    -0.07
     paylaş
    -0.06
     follando
    -0.06
     upstairs
    -0.06
     NRL
    -0.06
     دوب
    -0.06
    矿
    -0.06
     ей
    -0.06
    POSITIVE LOGITS
    極
    0.07
    Danger
    0.07
    Error
    0.06
    439
    0.06
    اند
    0.06
    innamon
    0.06
     joven
    0.06
     promotion
    0.06
    —and
    0.06
     شرقی
    0.06
    Act Density 0.000%

    No Known Activations