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

    Neuronpedia

    INDEX
    Explanations

    reach out for help

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     минуту
    0.48
    થમ
    0.47
     accentuated
    0.47
     ໜອງ
    0.46
     เอา
    0.45
    ᄈ
    0.44
     markedly
    0.44
    ைகளும்
    0.43
    稒
    0.43
     afbeelding
    0.43
    POSITIVE LOGITS
     via
    0.60
     for
    0.59
    📞
    0.57
     whenever
    0.57
     when
    0.55
     contact
    0.54
    ☎
    0.54
     if
    0.53
     directly
    0.52
     at
    0.52
    Act Density 0.081%

    No Known Activations