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

    Neuronpedia

    INDEX
    Explanations

    unsure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ?
    0.31
     summed
    0.30
     s
    0.30
     plant
    0.30
    ،
    0.29
    </b>
    0.29
     verir
    0.28
     Data
    0.28
     simple
    0.27
     strictly
    0.27
    POSITIVE LOGITS
     أنها
    0.42
    Ꮄ
    0.41
     আপনি
    0.39
    ли
    0.37
     שה
    0.37
     που
    0.36
    うまく
    0.36
    ку
    0.35
     että
    0.35
     ಅದು
    0.35
    Act Density 0.034%

    No Known Activations