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

    Neuronpedia

    INDEX
    Explanations

    private

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     UIB
    -0.07
     tekn
    -0.06
    .anchor
    -0.06
     berth
    -0.06
     уров
    -0.06
     rek
    -0.06
     Öğ
    -0.06
     katkı
    -0.06
    ัวเอง
    -0.06
     NAMES
    -0.06
    POSITIVE LOGITS
    рий
    0.07
    essenger
    0.07
     disappointment
    0.07
    ache
    0.07
    एम
    0.07
     hinter
    0.07
    اسي
    0.07
    ρη
    0.07
     proph
    0.06
     servants
    0.06
    Act Density 0.005%

    No Known Activations