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

    Neuronpedia

    INDEX
    Explanations

    code-related operations and API methods

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

    API code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     secundario
    -0.34
     enfans
    -0.34
     więc
    -0.34
    jąc
    -0.33
     blessé
    -0.33
     navideño
    -0.32
     jednocześnie
    -0.31
    collants
    -0.31
     bandeira
    -0.31
     wśród
    -0.31
    POSITIVE LOGITS
    .*")]
    0.85
     noDo
    0.72
     ligiloj
    0.65
    expandindo
    0.64
    contentLoaded
    0.61
    <unused79>
    0.60
     EconPapers
    0.60
    EndGlobalSection
    0.60
    <unused52>
    0.60
    <unused8>
    0.60
    Act Density 0.005%

    No Known Activations