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

    Neuronpedia

    INDEX
    Explanations

    input function calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    只会
    0.45
    ங்கா
    0.45
     tendrá
    0.45
     Hit
    0.44
     Rafa
    0.44
     avrà
    0.44
     Fight
    0.44
     लिखेंगे
    0.44
     হবে
    0.44
     Mate
    0.44
    POSITIVE LOGITS
    CES
    0.45
    Pers
    0.43
    troops
    0.43
    harap
    0.41
    ocrats
    0.41
    pers
    0.40
    ᅱ
    0.40
    paragus
    0.40
    scoped
    0.40
    text
    0.40
    Act Density 0.007%

    No Known Activations