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

    Neuronpedia

    INDEX
    Explanations

    procedural generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    楫
    0.54
    椑
    0.49
     florals
    0.47
    Bài
    0.47
    Lil
    0.46
     тексту
    0.46
    𝙏
    0.46
     номина
    0.46
     обли
    0.44
    బో
    0.43
    POSITIVE LOGITS
     জানায়
    0.52
    j
    0.50
     mantenere
    0.49
     asigur
    0.48
     smoot
    0.48
     maintain
    0.47
     haces
    0.46
    ized
    0.46
     solves
    0.46
     hasten
    0.46
    Act Density 0.054%

    No Known Activations