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

    Neuronpedia

    INDEX
    Explanations

    names, sourced, unsafe, watching

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     filmy
    0.45
     silice
    0.45
     Knopf
    0.42
     kre
    0.41
     Krebs
    0.40
     स्कू
    0.40
     clerg
    0.40
     antihist
    0.40
     stents
    0.39
     tema
    0.39
    POSITIVE LOGITS
     প্রস্তুত
    0.43
    ığımız
    0.41
     сове
    0.41
     booked
    0.41
    спублі
    0.39
     <!
    0.39
    arin
    0.39
    会の
    0.38
    ᱚ
    0.38
     அவரு
    0.38
    Act Density 0.000%

    No Known Activations