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

    Neuronpedia

    INDEX
    Explanations

    null and loading

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    য
    1.74
    ای
    1.69
     substantiated
    1.65
    见的
    1.61
    giveness
    1.58
    bindingFields
    1.57
    ោធ
    1.56
    䉽
    1.55
     catfish
    1.52
    襲
    1.52
    POSITIVE LOGITS
    t
    2.03
    tion
    1.75
    i
    1.33
    a
    1.33
    til
    1.29
    en
    1.29
    tos
    1.28
    in
    1.25
    tf
    1.25
    ið
    1.24
    Act Density 0.000%

    No Known Activations