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

    Neuronpedia

    INDEX
    Explanations

    technical terms and concepts related to research methodologies and practices

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

    systems or methods

    np_acts-logits-general · gemini-2.0-flash

    developed capable systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.75
     EconPapers
    -0.68
    MigrationBuilder
    -0.67
     noDo
    -0.65
    abestanden
    -0.61
     belongs
    -0.60
     مواليد
    -0.59
    nologue
    -0.57
    awtextra
    -0.57
    writeFieldEnd
    -0.57
    POSITIVE LOGITS
     capable
    1.33
     suitable
    1.19
     that
    1.15
     suited
    1.06
     able
    1.05
    capable
    1.00
     tailored
    0.99
     capaz
    0.94
    suitable
    0.92
     compatible
    0.89
    Act Density 1.059%

    No Known Activations