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

    Neuronpedia

    INDEX
    Explanations

    advice, safety, or warnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     requisition
    0.42
     Soccer
    0.38
     trolls
    0.38
     δυ
    0.38
     courses
    0.37
    requis
    0.37
     hipp
    0.37
     hai
    0.37
    biased
    0.37
    らしく
    0.37
    POSITIVE LOGITS
    neſs
    0.43
     Beob
    0.41
    chés
    0.40
    Yield
    0.39
    ar
    0.39
    nte
    0.38
    nemidophorus
    0.38
     Pfe
    0.38
    gern
    0.38
     Mā
    0.37
    Act Density 0.002%

    No Known Activations