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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating certainty or emphasis on specific points

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    don't get me wrong

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    riwal
    -0.35
     capri
    -0.33
     CONTIN
    -0.32
    src
    -0.31
    Prov
    -0.30
     ballast
    -0.30
     (=
    -0.29
     Quell
    -0.29
     CONS
    -0.29
    Intent
    -0.29
    POSITIVE LOGITS
    LEncoder
    0.63
    VersionUID
    0.63
     للاسماء
    0.60
    RTHOOK
    0.58
     الرياضيه
    0.58
     '\\;'
    0.57
    tinyos
    0.56
    AddTagHelper
    0.55
    RegistryLite
    0.55
     متعلقه
    0.54
    Act Density 0.083%

    No Known Activations