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

    Neuronpedia

    INDEX
    Explanations

    learn, implement, use, train, solve

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Чтобы
    0.40
     مبنی
    0.40
    to
    0.38
     =>
    0.37
     চেষ্টা
    0.37
     ל
    0.36
    드를
    0.36
     Ejec
    0.35
     Expr
    0.35
     "
    0.34
    POSITIVE LOGITS
     wszel
    0.41
     zarówno
    0.41
     numerosas
    0.40
     oneself
    0.39
     všechny
    0.39
    和
    0.36
     लिहाज
    0.36
     niż
    0.36
    馚
    0.36
     qualquer
    0.35
    Act Density 0.159%

    No Known Activations