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

    Neuronpedia

    INDEX
    Explanations

    URLs/code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    搔
    -0.07
    تفك
    -0.07
     jedis
    -0.07
    ߡ
    -0.07
    믕
    -0.07
     websocket
    -0.07
     sudden
    -0.07
    人在
    -0.07
     ciphertext
    -0.07
    经济学
    -0.07
    POSITIVE LOGITS
     vegan
    0.07
     Kerala
    0.07
    鼐
    0.07
    صراع
    0.07
    強い
    0.07
    avy
    0.07
    /",
    0.07
    .MenuItem
    0.07
    _idx
    0.06
    vy
    0.06
    Act Density 0.002%

    No Known Activations