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

    Neuronpedia

    INDEX
    Explanations

    function definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ફ
    0.96
     Sá
    0.84
    হন
    0.84
     возник
    0.82
    Ổ
    0.82
    хай
    0.82
     Realms
    0.82
     혹
    0.81
     menjalankan
    0.81
     Tets
    0.80
    POSITIVE LOGITS
    _
    0.73
    -
    0.71
     -
    0.70
    elas
    0.69
    elae
    0.64
     confidence
    0.63
     _
    0.62
    ',
    0.62
    at
    0.61
     lifting
    0.61
    Act Density 0.021%

    No Known Activations