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

    Neuronpedia

    INDEX
    Explanations

    medication or symptoms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wicklow
    0.52
     Comparable
    0.48
     (
    0.46
     Crowd
    0.45
     >
    0.41
    Crow
    0.40
     gx
    0.40
     Aprili
    0.40
    ഏ
    0.40
     HTMLElement
    0.39
    POSITIVE LOGITS
    ignores
    0.44
    浻
    0.43
    石
    0.42
     связа
    0.42
    immediate
    0.41
    𝗷
    0.41
     appreci
    0.40
    ığım
    0.40
    ချ
    0.40
    saint
    0.40
    Act Density 0.001%

    No Known Activations