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

    Neuronpedia

    INDEX
    Explanations

    terms related to media, information, and measurement in various disciplines

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

    counts, frequency, impact, receipt, density

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.59
    MessageTagHelper
    -0.59
    RTEE
    -0.57
    Rhestr
    -0.55
     Савезне
    -0.54
    GenerationType
    -0.54
    RenderAtEndOf
    -0.53
    ]=>
    -0.52
    AddTagHelper
    -0.51
     للاسماء
    -0.50
    POSITIVE LOGITS
     support
    0.51
     behavior
    0.50
     behaviors
    0.50
     with
    0.49
     for
    0.49
     expression
    0.48
     scores
    0.48
     dialogue
    0.46
     status
    0.46
     consideration
    0.46
    Act Density 0.068%

    No Known Activations