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

    Neuronpedia

    INDEX
    Explanations

    materials and their components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ，”
    0.42
    ，
    0.41
    ，“
    0.38
    ،
    0.37
    Т
    0.37
     Jahr
    0.36
    、『
    0.35
     eisen
    0.35
     heiß
    0.34
     Hör
    0.34
    POSITIVE LOGITS
    ad
    0.73
    is
    0.59
    ar
    0.59
    es
    0.54
    os
    0.52
    ed
    0.49
    al
    0.48
    en
    0.47
    ing
    0.46
    ap
    0.44
    Act Density 0.001%

    No Known Activations