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

    Neuronpedia

    INDEX
    Explanations

    common words and beginnings of phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    durationType
    0.59
    inios
    0.57
     دینا
    0.52
    ilded
    0.52
    клары
    0.50
    rases
    0.49
    𝖐
    0.48
     المعادله
    0.48
     financieros
    0.48
    liquidacion
    0.48
    POSITIVE LOGITS
     N
    0.61
     R
    0.60
     MySQL
    0.60
    ی
    0.58
     O
    0.57
     Debut
    0.56
    0.56
     it
    0.56
     Napa
    0.56
    G
    0.56
    Act Density 0.000%

    No Known Activations