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

    Neuronpedia

    INDEX
    Explanations

    location and date structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ྞ
    0.38
    itled
    0.37
    茥
    0.36
     heatmap
    0.36
     solenoid
    0.35
    पीरियंस
    0.35
     pulley
    0.35
     გამოყენ
    0.34
     ഉപയോഗ
    0.34
    หลด
    0.34
    POSITIVE LOGITS
     —
    0.55
     -
    0.44
     –
    0.44
    Reuters
    0.42
     --
    0.41
    Сегодня
    0.41
    April
    0.40
    October
    0.40
    June
    0.39
    July
    0.39
    Act Density 0.002%

    No Known Activations