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

    Neuronpedia

    INDEX
    Explanations

    numbers and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ون
    0.54
    وا
    0.54
    ج
    0.53
    </i>
    0.52
     rink
    0.48
    薈
    0.48
    </blockquote>
    0.47
     re
    0.47
    ัม
    0.47
    ين
    0.46
    POSITIVE LOGITS
     inconceivable
    0.54
    லோச
    0.49
    CharCode
    0.48
    decrease
    0.47
     negros
    0.47
    ların
    0.46
     домаћин
    0.45
     প্রয
    0.44
    stretch
    0.44
    Difficulty
    0.43
    Act Density 0.195%

    No Known Activations