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

    Neuronpedia

    INDEX
    Explanations

    quadratic forms and polynomials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    の
    0.63
    nya
    0.61
    の効果
    0.59
     macam
    0.57
    માં
    0.57
     toată
    0.57
    на
    0.56
    ის
    0.56
    اً
    0.56
     latérales
    0.55
    POSITIVE LOGITS
    H
    0.74
     \
    0.71
     spawned
    0.62
     REQUEST
    0.60
     И
    0.59
     |_{
    0.59
    !}{
    0.58
    I
    0.58
    N
    0.57
     (\
    0.56
    Act Density 0.001%

    No Known Activations