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

    Neuronpedia

    INDEX
    Explanations

    .amazon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     晴
    -0.07
    arsing
    -0.07
    vající
    -0.07
    Sparse
    -0.06
    305
    -0.06
    인지
    -0.06
    Fall
    -0.06
    Mil
    -0.06
     Zar
    -0.06
    攻击
    -0.06
    POSITIVE LOGITS
    oklyn
    0.08
     короб
    0.06
     ornament
    0.06
     Adrian
    0.06
    cript
    0.06
     فوق
    0.06
    urrect
    0.06
     adorn
    0.06
     validator
    0.06
    σιμοποι
    0.06
    Act Density 0.002%

    No Known Activations