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

    Neuronpedia

    INDEX
    Explanations

    city names and places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     or
    0.52
    s
    0.52
    ü
    0.51
     are
    0.51
    л
    0.48
    ą
    0.46
    í
    0.45
     oli
    0.42
    㮔
    0.42
     impuestos
    0.42
    POSITIVE LOGITS
    و
    0.57
    다
    0.47
    ної
    0.41
    在
    0.41
    ي
    0.40
    ot
    0.40
    ib
    0.39
     disorganized
    0.38
    もら
    0.38
    다라고
    0.38
    Act Density 0.000%

    No Known Activations