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

    Neuronpedia

    INDEX
    Explanations

    edible spirits, animation, alphabet

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    arious
    0.48
    ola
    0.46
    idden
    0.45
    ateful
    0.43
    onn
    0.43
     পারে
    0.42
    ite
    0.41
    era
    0.41
     r
    0.41
    hed
    0.40
    POSITIVE LOGITS
     നട
    0.56
     നേരി
    0.53
     Mạnh
    0.48
     tanıml
    0.47
     شہید
    0.47
     ادبی
    0.47
    肅
    0.45
    湁
    0.45
     dó
    0.44
     habitually
    0.44
    Act Density 0.001%

    No Known Activations