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

    Neuronpedia

    INDEX
    Explanations

    technical phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iation
    1.23
    ę
    1.21
     smelting
    1.20
     enqueue
    1.18
     transonic
    1.17
    dU
    1.16
    oviruses
    1.13
     overcast
    1.12
     queryString
    1.12
    ointments
    1.12
    POSITIVE LOGITS
    ِن
    1.09
    "."
    1.07
    ''_
    1.07
    觞
    1.00
    𝐮
    0.99
     पर्यंत
    0.98
    habalar
    0.98
     सीख
    0.98
    어
    0.98
    преки
    0.96
    Act Density 0.000%

    No Known Activations