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

    Neuronpedia

    INDEX
    Explanations

    before or after clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𒉺
    0.50
     Pér
    0.47
     perchè
    0.46
     Juárez
    0.44
     Pérez
    0.44
     현재
    0.44
     ಮಾ
    0.44
     ò
    0.43
     sā
    0.43
    );*/
    0.43
    POSITIVE LOGITS
    van
    0.46
    ST
    0.45
     checkIf
    0.45
     catheters
    0.45
    of
    0.43
    型
    0.42
     publiques
    0.41
    out
    0.41
    led
    0.41
    istes
    0.40
    Act Density 0.004%

    No Known Activations