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

    Neuronpedia

    INDEX
    Explanations

    explicit sexual descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     entreprises
    -0.07
     inside
    -0.07
     soup
    -0.06
    بن
    -0.06
    (document
    -0.06
     autumn
    -0.06
    _BASIC
    -0.06
     ,
    -0.06
     do
    -0.06
     insurance
    -0.06
    POSITIVE LOGITS
    ערות
    0.07
    _filepath
    0.07
     tả
    0.07
    akter
    0.07
    חס
    0.06
     Scar
    0.06
    ätt
    0.06
    向外
    0.06
     kicker
    0.06
    ⏎
    0.06
    Act Density 0.081%

    No Known Activations