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

    Neuronpedia

    INDEX
    Explanations

    numbers after code constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    2
    0.64
    4
    0.63
    1
    0.62
    3
    0.61
    7
    0.59
    6
    0.59
    5
    0.57
    9
    0.52
    8
    0.51
     the
    0.49
    POSITIVE LOGITS
    puede
    0.47
    er
    0.46
    zelfde
    0.45
     இருக்கலாம்
    0.45
    P
    0.45
    in
    0.43
    ﺹ
    0.43
    rugated
    0.42
     $\|
    0.42
     כן
    0.42
    Act Density 0.453%

    No Known Activations