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

    Neuronpedia

    INDEX
    Explanations

    references to programming elements, particularly those indicating creation, modification, and data structures

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

    end of turn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.52
    tagHelperRunner
    -0.51
    +#+
    -0.50
    protoimpl
    -0.47
    featureID
    -0.41
    awtextra
    -0.40
     kasarigan
    -0.39
    ⓧ
    -0.36
    AddTagHelper
    -0.36
    siven
    -0.36
    POSITIVE LOGITS
     greateſt
    0.51
     Infórmanos
    0.43
    ↹
    0.43
     beſt
    0.43
    íritu
    0.42
     faſt
    0.42
    FormTagHelper
    0.41
     escrit
    0.41
     ſmall
    0.41
     gyhoeddwyd
    0.40
    Act Density 0.272%

    No Known Activations