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

    Neuronpedia

    INDEX
    Explanations

    "said" or "explained" followed by a name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ਵ
    0.40
     Hopefully
    0.40
    ↵↵
    0.38
     असल्याचे
    0.38
     등
    0.36
     وهكذا
    0.36
    라는
    0.35
    ვილ
    0.35
    眽
    0.35
     courageous
    0.35
    POSITIVE LOGITS
    ڍ
    0.35
    Ꮨ
    0.34
    ой
    0.34
    сса
    0.32
    otin
    0.31
    algar
    0.31
     projectors
    0.30
     topi
    0.29
    estä
    0.29
    สู
    0.29
    Act Density 0.004%

    No Known Activations