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

    Neuronpedia

    INDEX
    Explanations

    ure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     цвет
    -0.07
    【
    -0.07
     dou
    -0.07
    dropdown
    -0.07
     Dre
    -0.07
    .sessions
    -0.06
    creds
    -0.06
    玉
    -0.06
    irected
    -0.06
     ремон
    -0.06
    POSITIVE LOGITS
     Indians
    0.06
    November
    0.06
    _catalog
    0.06
     +=↵
    0.06
     glanced
    0.05
     ("\
    0.05
     Hunting
    0.05
    ='.$
    0.05
    Fraction
    0.05
    수가
    0.05
    Act Density 0.001%

    No Known Activations