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

    Neuronpedia

    INDEX
    Explanations

    questions or inquiries with a focus on uncertainty or affirmation

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

    ' it is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jewództ
    -0.41
     Signalez
    -0.39
    InputModule
    -0.35
     transfieras
    -0.34
    서는
    -0.32
    iastical
    -0.32
     ویکی‌پدی
    -0.32
    SceneManagement
    -0.32
     médical
    -0.32
    UnitTesting
    -0.32
    POSITIVE LOGITS
    :✨
    0.56
    posedge
    0.54
     squared
    0.54
     Joe
    0.50
    getParam
    0.50
    cetines
    0.50
    ApiModelProperty
    0.49
    verdad
    0.49
    hithe
    0.49
     Hinsicht
    0.49
    Act Density 0.022%

    No Known Activations