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

    Neuronpedia

    INDEX
    Explanations

    say "adult/comedy"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     playful
    -0.07
    .Storage
    -0.07
     azi
    -0.07
     impon
    -0.07
    語
    -0.07
    /About
    -0.07
     sender
    -0.07
     Yukon
    -0.07
    .PNG
    -0.07
     uploads
    -0.07
    POSITIVE LOGITS
     relentlessly
    0.09
     свеж
    0.09
    Personally
    0.08
     hopefully
    0.08
    ركز
    0.08
     dried
    0.08
    fresh
    0.08
     meticulously
    0.08
     cringe
    0.08
    CENTER
    0.08
    Act Density 0.011%

    No Known Activations