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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ربية
    -0.07
    _COST
    -0.07
    copies
    -0.06
    illing
    -0.06
    -flow
    -0.06
    ,s
    -0.06
     Cathy
    -0.06
    Dismiss
    -0.06
     cloth
    -0.06
     dialect
    -0.06
    POSITIVE LOGITS
     administer
    0.07
     recept
    0.07
     sní
    0.07
    reon
    0.06
     run
    0.06
     tonumber
    0.06
    ılmıştır
    0.06
     少
    0.06
     Corbyn
    0.06
     získat
    0.06
    Act Density 0.017%

    No Known Activations