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

    Neuronpedia

    INDEX
    Explanations

    character description, planning, code initialization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     conformément
    0.38
     interstitiis
    0.38
    氬
    0.38
     entièrement
    0.38
     personalizado
    0.38
    लॉक
    0.37
     personalise
    0.36
    根據
    0.36
    스타그램
    0.36
    られています
    0.36
    POSITIVE LOGITS
     Jimmy
    0.43
     காரண
    0.42
     Amish
    0.41
    ḏ
    0.40
     Hannah
    0.38
    allic
    0.38
     Rh
    0.38
     Lily
    0.37
     drum
    0.37
     Reasons
    0.37
    Act Density 0.000%

    No Known Activations