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

    Neuronpedia

    INDEX
    Explanations

    numbered sections and items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     निसाब
    0.39
    ⺠
    0.38
    kbeta
    0.35
     wartość
    0.35
    टेज
    0.35
    褸
    0.34
    koliko
    0.34
    σιο
    0.34
    tBleStatus
    0.34
     każdym
    0.34
    POSITIVE LOGITS
     "
    0.47
     (
    0.38
     '
    0.37
     “
    0.35
     The
    0.34
     |
    0.33
    ,
    0.33
     -
    0.33
    ↵↵
    0.33
     known
    0.32
    Act Density 0.037%

    No Known Activations