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

    Neuronpedia

    INDEX
    Explanations

    plot, filter, ta

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    absValue
    0.38
    㤟
    0.38
    醎
    0.38
     preocupaciones
    0.38
    ฤ
    0.38
     ennemis
    0.37
    Painted
    0.36
     berasal
    0.35
     கிடைத்தது
    0.35
    လေ
    0.35
    POSITIVE LOGITS
     T
    0.39
    filter
    0.37
    W
    0.36
     Waller
    0.36
     isinstance
    0.35
     (
    0.35
     filter
    0.34
     O
    0.34
     segment
    0.34
     Wall
    0.34
    Act Density 0.002%

    No Known Activations