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

    Neuronpedia

    INDEX
    Explanations

    Bali

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    的小
    -0.06
     scrut
    -0.06
    ,↵↵
    -0.06
     Пав
    -0.06
    nave
    -0.06
    .hex
    -0.06
    Mac
    -0.06
     Cumhur
    -0.06
    ولة
    -0.06
     lst
    -0.06
    POSITIVE LOGITS
     Bali
    0.12
     Goa
    0.10
    bakan
    0.07
     sitio
    0.07
    340
    0.06
    い
    0.06
    .databind
    0.06
     upcoming
    0.06
     exponent
    0.06
    .no
    0.06
    Act Density 0.001%

    No Known Activations