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

    Neuronpedia

    INDEX
    Explanations

    Bryan followed by name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ’
    -2.61
     algunos
    -2.56
     großen
    -2.33
     Kontexten
    -2.27
     puzzling
    -2.27
    上司
    -2.25
    ஂ
    -2.25
     purported
    -2.25
     presumed
    -2.20
     ensino
    -2.19
    POSITIVE LOGITS
    us
    3.27
    up
    3.08
    0
    2.78
    r
    2.69
    ss
    2.59
    7
    2.58
    6
    2.56
    am
    2.47
    2
    2.45
    amp
    2.44
    Act Density 0.002%

    No Known Activations