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

    Neuronpedia

    INDEX
    Explanations

    step-by-step thinking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RO
    1.40
    OC
    1.20
    я
    1.20
    ль
    1.17
    кі
    1.02
    7
    1.02
    RA
    1.01
    ET
    0.99
    5
    0.99
    ESO
    0.97
    POSITIVE LOGITS
     conç
    1.18
     amélior
    1.15
    âmica
    1.12
     وکړئ
    1.09
     interchangeable
    1.08
    iração
    1.07
    ম
    1.07
    म
    1.06
    💭
    1.06
    تن
    1.05
    Act Density 0.897%

    No Known Activations