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

    Neuronpedia

    INDEX
    Explanations

    phrases related to enjoyment and personal engagement

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

    purpose for action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ɵɵelementStart
    -0.45
     kasarigan
    -0.44
    -0.41
    ngdoc
    -0.41
    catch
    -0.40
     regulation
    -0.39
     measured
    -0.39
     delivery
    -0.38
     Mira
    -0.38
     AssemblyTitle
    -0.38
    POSITIVE LOGITS
     <<<<<<<<<<<<<<
    0.63
    AndEndTag
    0.51
     desmotivaciones
    0.50
    :✨
    0.50
     للاسماء
    0.48
     Grecs
    0.48
    IntoConstraints
    0.47
    HasForeignKey
    0.46
     Grüsse
    0.46
    RenderAtEndOf
    0.44
    Act Density 0.079%

    No Known Activations