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

    Neuronpedia

    INDEX
    Explanations

    instances of personal input or acknowledgment in the text

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

    mathematical expressions and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    unteer
    -0.69
    AsUp
    -0.58
    osocial
    -0.55
     actionMode
    -0.54
    aarrggbb
    -0.52
    PerformLayout
    -0.52
    FormState
    -0.52
     desmotivaciones
    -0.50
     pylab
    -0.49
    addPreferred
    -0.48
    POSITIVE LOGITS
     cherchés
    0.45
    LookAnd
    0.44
    IVEREF
    0.40
    Hentet
    0.39
     שוליים
    0.39
    цездатний
    0.38
     незавершена
    0.38
    migrationBuilder
    0.38
    Diweddarwch
    0.37
     للمعارف
    0.37
    Act Density 0.013%

    No Known Activations