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

    Neuronpedia

    INDEX
    Explanations

    biggest, larger, huge + noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    tır
    0.66
     pornography
    0.60
     restrooms
    0.60
     soigne
    0.59
    tam
    0.59
     overheat
    0.58
     unglaublich
    0.58
     verschiedene
    0.58
     különböző
    0.58
     kala
    0.57
    POSITIVE LOGITS
    ن
    0.65
    Notwithstanding
    0.56
    czeniu
    0.56
    ীর
    0.56
     frankly
    0.52
    Nag
    0.52
    说
    0.51
    ⇒
    0.51
     поэтому
    0.50
    THING
    0.50
    Act Density 0.405%

    No Known Activations