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

    Neuronpedia

    INDEX
    Explanations

    around the, Add to, Jack Kelly, and sore

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ties
    1.08
    পা
    1.07
     benefic
    1.00
    cott
    1.00
     gli
    0.99
     menores
    0.99
     ce
    0.94
    掠
    0.94
    dt
    0.94
    掌
    0.92
    POSITIVE LOGITS
    oculars
    1.36
    ים
    1.30
    噜
    1.29
    ﻡ
    1.28
    ర్థిక
    1.26
    哝
    1.25
    ethyst
    1.24
    körper
    1.24
    骖
    1.23
    רי
    1.22
    Act Density 0.000%

    No Known Activations