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

    Neuronpedia

    INDEX
    Explanations

    syntactic structures and formatting cues in code

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

    sanity check

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     certainty
    -1.01
     guaranteed
    -0.91
     assured
    -0.90
     guarantee
    -0.83
     sure
    -0.81
     assurance
    -0.76
    certainty
    -0.74
     certeza
    -0.70
     certitude
    -0.69
     guarantees
    -0.69
    POSITIVE LOGITS
     ArrayAdapter
    0.57
    Portail
    0.54
     FetchType
    0.53
    AnchorTagHelper
    0.48
    RTLR
    0.48
     snippetHide
    0.47
     Italijanski
    0.47
    ModelSerializer
    0.47
    JpaRepository
    0.47
    migrationBuilder
    0.47
    Act Density 0.008%

    No Known Activations