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

    Neuronpedia

    INDEX
    Explanations

    been

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _stand
    -0.06
     neutr
    -0.06
    ّم
    -0.06
     "\"
    -0.06
     før
    -0.06
     factions
    -0.06
    виж
    -0.06
     Shopify
    -0.06
     VIP
    -0.05
    ้าง
    -0.05
    POSITIVE LOGITS
     European
    0.07
    cheap
    0.06
    straight
    0.06
    ്
    0.06
    ubu
    0.06
     educ
    0.06
     follower
    0.06
    Expression
    0.06
     diversity
    0.06
    InnerText
    0.06
    Act Density 0.000%

    No Known Activations