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

    Neuronpedia

    INDEX
    Explanations

    sexually explicit content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ‌آ
    -0.06
    кур
    -0.06
    Cook
    -0.06
    (contents
    -0.06
     fout
    -0.06
     �
    -0.06
     Locker
    -0.06
    页面存档备份
    -0.06
     ول
    -0.05
    (done
    -0.05
    POSITIVE LOGITS
    _nombre
    0.08
    Sphere
    0.07
     стол
    0.07
    _Server
    0.07
    σία
    0.07
     Αρχ
    0.07
     shortest
    0.06
    uiten
    0.06
     ihrer
    0.06
    ै।↵↵
    0.06
    Act Density 0.025%

    No Known Activations