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

    Neuronpedia

    INDEX
    Explanations

    hostels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     scammers
    0.44
     immisc
    0.41
     TSC
    0.41
     현실
    0.41
     impurities
    0.39
    ሠ
    0.39
     countDown
    0.39
    mersible
    0.38
     realities
    0.38
     በዚህ
    0.38
    POSITIVE LOGITS
     পেই
    0.38
     Fern
    0.36
    RP
    0.36
     RP
    0.36
    اعة
    0.35
     الصح
    0.35
     নাই
    0.34
    pees
    0.34
    ާއ
    0.34
     ecológica
    0.34
    Act Density 0.000%

    No Known Activations