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

    Neuronpedia

    INDEX
    Explanations

    numerical ranges or scales, particularly related to measurements

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

    year ranges and centuries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.46
    StructEnd
    -0.40
     okuyayım
    -0.39
    Dazu
    -0.38
     hoarding
    -0.38
    ällor
    -0.38
     Himo
    -0.38
    HomeAsUp
    -0.38
     articol
    -0.37
    Tikang
    -0.37
    POSITIVE LOGITS
     CascadeType
    0.52
     appunto
    0.52
    ymce
    0.50
    antaranya
    0.48
    entraînement
    0.47
    amitié
    0.41
    rath
    0.41
    feinander
    0.40
    sproz
    0.40
    entraî
    0.40
    Act Density 0.013%

    No Known Activations