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

    Neuronpedia

    INDEX
    Explanations

    expressions of amusement or lightheartedness

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

    positive informal expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    |}{
    -0.36
    >),
    -0.34
    UnitTesting
    -0.33
    ']),
    -0.32
    -0.31
     feit
    -0.31
    -0.31
     tij
    -0.31
    )),
    -0.31
    ))]
    -0.30
    POSITIVE LOGITS
    исленность
    0.68
    tiérrez
    0.66
     Վերցված
    0.63
    Referencie
    0.63
    Viited
    0.60
    الدراسه
    0.60
    arangay
    0.60
     saites
    0.60
    ázaro
    0.59
    BibitemShut
    0.59
    Act Density 0.027%

    No Known Activations