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

    Neuronpedia

    INDEX
    Explanations

    Code/formatting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lação
    -0.08
    .cons
    -0.08
    တွက်
    -0.08
    -0.08
     últimas
    -0.08
     값을
    -0.08
     finals
    -0.08
    是多少
    -0.08
     нужна
    -0.08
     எப்படி
    -0.08
    POSITIVE LOGITS
    odio
    0.08
    arım
    0.08
    ardi
    0.08
    Knight
    0.08
    メント
    0.08
    boj
    0.07
    <|endoftext|>
    0.07
    man
    0.07
    arya
    0.07
     disconnected
    0.07
    Act Density 0.518%
    No Known Activations