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

    Neuronpedia

    INDEX
    Explanations

    LaTeX for mathematics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     سبب
    0.52
    铬
    0.50
     egyéb
    0.48
     كال
    0.48
     Verkehrs
    0.48
    文学
    0.48
    図
    0.47
    estellt
    0.46
     لیتے
    0.46
     পদার্থের
    0.46
    POSITIVE LOGITS
     for
    0.57
    isman
    0.55
     i
    0.54
    iz
    0.48
     aspiring
    0.47
     exporting
    0.47
    na
    0.46
    il
    0.46
    ี
    0.46
     central
    0.45
    Act Density 0.008%

    No Known Activations