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

    Neuronpedia

    INDEX
    Explanations

    Thanks for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ระ
    0.42
     និង
    0.41
     लक्षात
    0.41
     nitric
    0.41
     glycos
    0.40
     altitudes
    0.40
     रि
    0.40
     minimization
    0.40
     histidine
    0.40
    ành
    0.39
    POSITIVE LOGITS
    Gracias
    0.63
    ה
    0.56
    ла
    0.53
     for
    0.53
     to
    0.52
    感谢
    0.52
     Gracias
    0.50
     Dade
    0.50
     teşekkür
    0.50
     from
    0.49
    Act Density 0.010%

    No Known Activations