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

    Neuronpedia

    INDEX
    Explanations

    terms related to privacy policies and user agreements

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

    agreeing to terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PerPage
    -0.35
     ever
    -0.35
    footed
    -0.34
     exotic
    -0.33
    planted
    -0.33
     surla
    -0.33
    如何在
    -0.32
     prop
    -0.32
    Leit
    -0.32
    ever
    -0.32
    POSITIVE LOGITS
     acceptance
    0.71
    MigrationBuilder
    0.69
     aceptación
    0.69
     by
    0.68
     Teilnahme
    0.61
    By
    0.60
     participation
    0.59
     osallist
    0.58
     By
    0.58
     agreeing
    0.57
    Act Density 0.088%

    No Known Activations