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

    Neuronpedia

    INDEX
    Explanations

    removing unwanted things

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .touches
    -0.07
     Vk
    -0.07
    _indices
    -0.07
    ethereum
    -0.06
    -0.06
     codecs
    -0.06
    ока
    -0.06
     з
    -0.06
     Weak
    -0.06
     vortex
    -0.06
    POSITIVE LOGITS
     المدينة
    0.07
    ็ค
    0.07
    主人
    0.07
     Rim
    0.07
     rewritten
    0.07
     pediatric
    0.06
     Аль
    0.06
     ALT
    0.06
    comic
    0.06
    (receiver
    0.06
    Act Density 0.019%

    No Known Activations