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

    Neuronpedia

    INDEX
    Explanations

    unit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Muham
    -0.06
    Encode
    -0.06
    ’a
    -0.06
    _nh
    -0.06
     '"'
    -0.06
    lot
    -0.06
    omin
    -0.06
    Vin
    -0.06
    _bot
    -0.06
    .spotify
    -0.06
    POSITIVE LOGITS
     swimming
    0.06
    buscar
    0.06
     bdsm
    0.06
     Pour
    0.06
    保护
    0.06
    نسا
    0.06
     Pussy
    0.06
     Credits
    0.06
    Este
    0.06
     deception
    0.06
    Act Density 0.000%

    No Known Activations