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

    Neuronpedia

    INDEX
    Explanations

    Greek and Thai conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nombreuses
    0.71
     গোপন
    0.66
     хто
    0.64
    ിലേക്ക്
    0.64
    一些
    0.64
    亜
    0.62
    亰
    0.62
    공
    0.62
     ది
    0.62
    Checker
    0.62
    POSITIVE LOGITS
    好好
    0.74
     aligning
    0.71
    ponding
    0.71
     Pourtant
    0.69
     bite
    0.68
    ínio
    0.68
     μέσα
    0.68
     Bite
    0.67
     psyche
    0.67
     interacts
    0.67
    Act Density 0.001%

    No Known Activations