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

    Neuronpedia

    INDEX
    Explanations

    alphabets and letters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     suced
    -0.09
    数据库
    -0.08
     Serm
    -0.08
    任何
    -0.07
    spannung
    -0.07
    转换
    -0.07
    ({},
    -0.07
    spread
    -0.07
    स्प
    -0.07
    莉
    -0.07
    POSITIVE LOGITS
     propose
    0.08
    _unused
    0.08
    وفمبر
    0.08
    _reserved
    0.08
     используются
    0.08
    يد
    0.08
    ائر
    0.08
     ضر
    0.08
     proposes
    0.08
    ulah
    0.08
    Act Density 0.005%

    No Known Activations