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

    Neuronpedia

    INDEX
    Explanations

    Mathematical/physics notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pref
    -0.07
    ในท
    -0.06
     yolc
    -0.06
    ocy
    -0.06
     گرف
    -0.06
    ewan
    -0.06
    .TAG
    -0.06
    arcy
    -0.06
     ness
    -0.06
    <g
    -0.06
    POSITIVE LOGITS
     Chuck
    0.07
    堆
    0.06
    Virginia
    0.06
     delivering
    0.06
    ))))↵↵
    0.06
     php
    0.06
    ISION
    0.06
    (Android
    0.06
    Sdk
    0.06
     Corruption
    0.06
    Act Density 0.002%

    No Known Activations