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

    Neuronpedia

    INDEX
    Explanations

    announce

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﺪ
    0.79
    。
    0.79
    دو
    0.70
    ده
    0.67
     உண
    0.66
    دى
    0.66
     cinq
    0.66
    ER
    0.64
    دی
    0.64
    '
    0.63
    POSITIVE LOGITS
     theyre
    0.58
     selepas
    0.58
     externas
    0.54
    Tech
    0.54
    Sha
    0.54
     penelitian
    0.53
    larini
    0.53
     pēc
    0.53
     botched
    0.53
     iš
    0.52
    Act Density 0.001%

    No Known Activations