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

    Neuronpedia

    INDEX
    Explanations

    AI, acceptance, copy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    boundaries
    0.47
    UARY
    0.46
     шей
    0.46
    ilians
    0.46
    borders
    0.46
    氀
    0.45
     автора
    0.45
     گرفتن
    0.43
    нія
    0.42
    jería
    0.42
    POSITIVE LOGITS
    u
    0.47
    țe
    0.42
     Cross
    0.41
    </span>
    0.39
    $(
    0.39
    `),
    0.39
    `,
    0.39
    '];
    0.39
     Cree
    0.38
    <
    0.38
    Act Density 0.155%

    No Known Activations