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

    Neuronpedia

    INDEX
    Explanations

    .Method

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .cover
    -0.07
     ¿
    -0.07
    רפואה
    -0.07
     الأجنب
    -0.07
     Ct
    -0.07
    菰
    -0.07
    Ẽ
    -0.07
    燠
    -0.07
     penn
    -0.06
     slee
    -0.06
    POSITIVE LOGITS
    th
    0.07
     tính
    0.07
    .newLine
    0.07
    _prev
    0.06
     extremist
    0.06
     transformations
    0.06
    át
    0.06
     elimination
    0.06
     Hera
    0.06
    resh
    0.06
    Act Density 0.001%

    No Known Activations