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

    Neuronpedia

    INDEX
    Explanations

    items and their associations in various contexts

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

    endthenthereit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    -0.64
    ↵↵
    -0.61
     and
    -0.48
     but
    -0.42
    ,
    -0.42
     kanan
    -0.40
    ↵↵↵
    -0.39
    I
    -0.39
     more
    -0.38
    <eos>
    -0.38
    POSITIVE LOGITS
    featureID
    0.77
    sizeCache
    0.77
    0.72
     Paglinawan
    0.72
     تضيفلها
    0.71
     betweenstory
    0.71
     estekak
    0.66
     jsPsych
    0.65
     Exactos
    0.65
     незавершена
    0.63
    Act Density 0.283%

    No Known Activations