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

    Neuronpedia

    INDEX
    Explanations

    Who

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _attrs
    -0.06
     bul
    -0.06
    İR
    -0.06
     Hòa
    -0.06
     Kỳ
    -0.06
    ังจาก
    -0.06
    кур
    -0.06
     Ukra
    -0.06
    396
    -0.06
     plenty
    -0.06
    POSITIVE LOGITS
    atories
    0.07
    forms
    0.06
    .dumps
    0.06
    (SQL
    0.06
     verbally
    0.06
    .other
    0.06
     consumption
    0.06
    akin
    0.06
    (left
    0.06
    ю
    0.06
    Act Density 0.001%

    No Known Activations