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

    Neuronpedia

    INDEX
    Explanations

    starts with "a" or "the"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    اق
    0.68
     desperate
    0.65
    на
    0.63
     Czy
    0.63
     Sare
    0.62
    weil
    0.62
     gel
    0.62
     OT
    0.62
    ان
    0.61
    Competing
    0.61
    POSITIVE LOGITS
     popupButton
    0.95
    릭터
    0.90
     toxicants
    0.86
     phonons
    0.84
     Bén
    0.83
    సుకోవ
    0.82
     lipoproteins
    0.80
    诶
    0.80
     nhắc
    0.78
     Noeud
    0.78
    Act Density 0.000%

    No Known Activations