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

    Neuronpedia

    INDEX
    Explanations

    clockwise and counterclockwise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     পারব
    0.45
     fluence
    0.42
    motions
    0.38
    autant
    0.38
     emote
    0.38
     подходя
    0.38
     وقال
    0.37
    দ্‌
    0.37
     verwend
    0.37
     geeign
    0.37
    POSITIVE LOGITS
    True
    0.40
     इंट
    0.39
     indeed
    0.39
    태
    0.38
    Shakespeare
    0.38
    Aging
    0.38
    Tag
    0.36
    ڈین
    0.36
    Gandhi
    0.36
    漬
    0.36
    Act Density 0.000%

    No Known Activations