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

    Neuronpedia

    INDEX
    Explanations

    references to specific dates and numerical data

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

    months and years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     queſta
    -1.01
     Италијани
    -0.87
     indígen
    -0.74
     faſt
    -0.70
     Normdatei
    -0.69
    adaptiveStyles
    -0.68
     ſei
    -0.68
     ſou
    -0.68
     geſch
    -0.67
    -0.67
    POSITIVE LOGITS
     
    0.54
    -
    0.46
     the
    0.44
     On
    0.43
    '
    0.42
    _
    0.42
     gritos
    0.42
    The
    0.42
    :
    0.42
       
    0.41
    Act Density 0.052%

    No Known Activations