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

    Neuronpedia

    INDEX
    Explanations

    article openings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Adem
    -0.08
     рабоч
    -0.08
     ↵        ↵
    -0.08
    িউ
    -0.08
     рабочих
    -0.08
     ابتد
    -0.08
     Apenas
    -0.07
     অনুভ
    -0.07
    ↵        ↵
    -0.07
    -mus
    -0.07
    POSITIVE LOGITS
    さん
    0.08
     MD
    0.08
    �
    0.07
     Turtle
    0.07
    ประเทศไทย
    0.07
    เฟ
    0.07
    yi
    0.07
     Ltd
    0.07
     대표
    0.07
    MD
    0.07
    Act Density 0.311%

    No Known Activations