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

    Neuronpedia

    INDEX
    Explanations

    IEEE

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     AMP
    -0.07
    踪
    -0.07
     שגם
    -0.07
    <User
    -0.07
     suspect
    -0.07
     wall
    -0.06
     vigilant
    -0.06
    机动
    -0.06
     U
    -0.06
    اخت
    -0.06
    POSITIVE LOGITS
     yelled
    0.07
    OfYear
    0.07
    .UUID
    0.07
    WebpackPlugin
    0.07
    磉
    0.07
    _lahir
    0.06
    ✨
    0.06
     meddling
    0.06
     الحصول
    0.06
     bliss
    0.06
    Act Density 0.003%

    No Known Activations