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

    Neuronpedia

    INDEX
    Explanations

    references to reading or reviewing content

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

    reading reviews or content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    -0.35
    <eos>
    -0.33
    /
    -0.32
    fillType
    -0.32
    Cubit
    -0.31
    ällningar
    -0.30
    -
    -0.29
    cvtColor
    -0.28
    odeon
    -0.28
     and
    -0.28
    POSITIVE LOGITS
    ंदीखरीदारी
    0.72
    expandindo
    0.69
     Numerade
    0.69
     surla
    0.69
     estekak
    0.68
     صوتيه
    0.67
     <<<<<<<<<<<<<<
    0.67
     noDo
    0.64
     Autorisations
    0.63
     وتسجيلات
    0.61
    Act Density 0.058%

    No Known Activations