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

    Neuronpedia

    INDEX
    Explanations

    following the letter '0'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     turnover
    0.40
     itens
    0.40
     مشاهد
    0.39
     nouve
    0.38
     calitate
    0.38
     threatened
    0.37
    சாமி
    0.37
     horseradish
    0.37
     ঘটবে
    0.37
     amea
    0.36
    POSITIVE LOGITS
    ื่ม
    0.40
    arian
    0.39
    arias
    0.39
    たくさん
    0.38
    Allow
    0.37
    hashtag
    0.37
    血
    0.37
     распа
    0.36
     correcting
    0.36
     Gla
    0.36
    Act Density 0.000%

    No Known Activations