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

    Neuronpedia

    INDEX
    Explanations

    he's

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     passports
    -0.09
    olygon
    -0.08
     passport
    -0.08
     ude
    -0.08
     salarial
    -0.08
     photographer
    -0.08
     fotogra
    -0.08
     distrib
    -0.08
    leness
    -0.08
    电话号码
    -0.08
    POSITIVE LOGITS
     aggressively
    0.08
    YPT
    0.08
     bursts
    0.08
     aggression
    0.08
     int
    0.07
     Booster
    0.07
     죽
    0.07
     Elder
    0.07
     attempt
    0.07
     אבל
    0.07
    Act Density 0.001%

    No Known Activations