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

    Neuronpedia

    INDEX
    Explanations

    software development and design

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1.46
     theses
    1.09
    ाम
    1.06
    зной
    1.02
    ス
    1.02
     I
    1.01
    いました
    1.00
    椛
    1.00
    外
    0.98
    いない
    0.98
    POSITIVE LOGITS
    <0x80>
    1.55
    L
    1.52
    K
    1.51
    an
    1.39
    ור
    1.39
    T
    1.37
    H
    1.37
    F
    1.36
    N
    1.31
    B
    1.31
    Act Density 0.056%

    No Known Activations