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

    Neuronpedia

    INDEX
    Explanations

    function and lambda signatures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    맇
    0.47
     организация
    0.45
     utilising
    0.44
     организаций
    0.44
    onese
    0.43
     innovating
    0.43
    𝚆
    0.43
    スタンド
    0.42
    위원회
    0.42
     технология
    0.42
    POSITIVE LOGITS
     dà
    0.54
     Test
    0.52
     Park
    0.51
     Tour
    0.51
     forfait
    0.50
    oski
    0.49
     dále
    0.49
    a
    0.48
     da
    0.48
    ก
    0.48
    Act Density 0.000%

    No Known Activations