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

    Neuronpedia

    INDEX
    Explanations

    two circles between

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     свер
    0.40
    objectManager
    0.40
    либо
    0.38
    मू
    0.38
    ีย์
    0.38
     MAM
    0.38
     खंड
    0.38
    toBe
    0.38
    亘
    0.37
     GÉN
    0.37
    POSITIVE LOGITS
     ilustraciones
    0.42
     privile
    0.39
     replies
    0.39
     privilegi
    0.38
     văn
    0.37
     transcripts
    0.37
     wartość
    0.37
     시간
    0.37
     privil
    0.37
     parlé
    0.36
    Act Density 0.001%

    No Known Activations