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

    Neuronpedia

    INDEX
    Explanations

    paradox and irony

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    is
    0.63
     nonradiative
    0.61
    le
    0.59
     vårt
    0.59
    ens
    0.59
    te
    0.57
     సా
    0.57
    गरानी
    0.57
    irik
    0.57
    ings
    0.57
    POSITIVE LOGITS
     paradox
    0.87
     paradoxical
    0.86
     Paradox
    0.76
    یر
    0.75
    ۲
    0.75
    ی
    0.73
     inconsistency
    0.68
    矛盾
    0.68
    מ
    0.67
     fonctionnement
    0.65
    Act Density 0.098%

    No Known Activations