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

    Neuronpedia

    INDEX
    Explanations

    tip

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     آماده
    -0.07
     sync
    -0.07
     Poh
    -0.07
     молод
    -0.06
     حال
    -0.06
    Fast
    -0.06
    TAIL
    -0.06
    �
    -0.06
    	Name
    -0.06
     race
    -0.06
    POSITIVE LOGITS
    inding
    0.06
    obra
    0.06
    ERVE
    0.06
    /package
    0.06
     поверхность
    0.06
    atl
    0.05
    alet
    0.05
    amic
    0.05
    hiba
    0.05
    cdf
    0.05
    Act Density 0.003%

    No Known Activations