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

    Neuronpedia

    INDEX
    Explanations

    be able to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    at
    0.67
    to
    0.64
    س
    0.62
    ok
    0.61
    ik
    0.60
    ong
    0.59
    oo
    0.59
    res
    0.57
    op
    0.57
    wo
    0.56
    POSITIVE LOGITS
    đena
    0.61
    GONDOR
    0.55
    GetService
    0.51
     autorità
    0.49
     dumpster
    0.48
     κάνει
    0.48
     বিষয়ের
    0.48
    )*((
    0.48
    ꗥ
    0.48
     படிக்க
    0.48
    Act Density 0.000%

    No Known Activations