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

    Neuronpedia

    INDEX
    Explanations

    specific details and actions related to objects and their interactions in various contexts

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

    at, photos, front, champagne, in, soles, flashing, bat, shirt, yell

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     starting
    -0.29
     suro
    -0.29
     representing
    -0.28
    wness
    -0.28
     structure
    -0.27
    随
    -0.27
    \
    -0.26
     Định
    -0.26
     Ni
    -0.25
    <
    -0.25
    POSITIVE LOGITS
    Autoritní
    0.87
     autorytatywna
    0.84
     Савезне
    0.79
     Wikimedijinoj
    0.79
     Administrativna
    0.75
     Италијани
    0.74
    IntoConstraints
    0.73
    хьтан
    0.71
    IsContent
    0.69
    лтемелер
    0.68
    Act Density 0.224%

    No Known Activations