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

    Neuronpedia

    INDEX
    Explanations

    continuous deformation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ي
    0.66
     soluzioni
    0.59
    এবং
    0.56
    י
    0.54
    ২০
    0.53
    報導
    0.53
     giust
    0.52
     améliorer
    0.50
    Ι
    0.50
    ଶ
    0.50
    POSITIVE LOGITS
    dh
    0.54
    kh
    0.52
    nge
    0.50
    emic
    0.49
    rq
    0.49
    mk
    0.48
    buk
    0.47
    iss
    0.46
    umin
    0.46
    reten
    0.46
    Act Density 0.000%

    No Known Activations