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

    Neuronpedia

    INDEX
    Explanations

    location identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    0.72
    -
    0.71
     con
    0.68
    are
    0.67
    ش
    0.65
    (
    0.64
    .
    0.63
     cri
    0.61
     dispon
    0.58
     ned
    0.58
    POSITIVE LOGITS
    এর
    1.34
    tsó
    0.91
    arrerol
    0.86
    ˏ
    0.86
    ग्विजय
    0.85
    Settl
    0.85
    –
    0.84
     ै
    0.84
     веществ
    0.81
     строк
    0.80
    Act Density 0.352%

    No Known Activations