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

    Neuronpedia

    INDEX
    Explanations

    Go context.Context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    लिस्ट
    0.46
    屯
    0.41
    ندس
    0.40
    нями
    0.40
     Donkey
    0.39
     rusk
    0.39
     кеңсе
    0.39
     பக்த
    0.38
    DistanceFrom
    0.38
    بية
    0.38
    POSITIVE LOGITS
     (
    0.45
     ->
    0.40
    Ö
    0.39
    ‚
    0.39
    iah
    0.38
    š
    0.37
    .(
    0.36
     (~
    0.36
    ￢
    0.36
    %=
    0.35
    Act Density 0.000%

    No Known Activations