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

    Neuronpedia

    INDEX
    Explanations

    research lab

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ข้อ
    0.48
    under
    0.42
    つつ
    0.41
     Section
    0.40
    unless
    0.40
    ുകെ
    0.40
    cuss
    0.40
    ാം
    0.39
     เ
    0.39
    ESH
    0.39
    POSITIVE LOGITS
    ه
    0.57
    </strong>
    0.55
     Ainda
    0.55
     gratuitos
    0.54
     gratuito
    0.54
     imprimir
    0.52
     entend
    0.52
     LMF
    0.51
    </sub>
    0.50
    ත්
    0.50
    Act Density 0.000%

    No Known Activations