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

    Neuronpedia

    INDEX
    Explanations

    asking how

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Gerv
    0.52
     почвы
    0.51
     Hector
    0.50
     enzimas
    0.50
     covari
    0.50
     Sling
    0.50
    ভিশ
    0.49
     ଦ
    0.49
     Clover
    0.49
     خوشه
    0.49
    POSITIVE LOGITS
    How
    0.61
     how
    0.57
     How
    0.55
    怎么
    0.50
    Key
    0.46
    L
    0.46
    위
    0.46
    怎
    0.46
    Wie
    0.46
    Pen
    0.45
    Act Density 0.079%

    No Known Activations