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

    Neuronpedia

    INDEX
    Explanations

    suggestions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    晡
    -0.08
    .close
    -0.08
     matériel
    -0.08
    update
    -0.08
    zip
    -0.07
     преим
    -0.07
     mask
    -0.07
    .nama
    -0.07
    -end
    -0.07
    ellung
    -0.07
    POSITIVE LOGITS
    Ԁ
    0.07
    𬳽
    0.07
    넛
    0.07
     приня
    0.07
    ocrine
    0.07
     Ferdinand
    0.07
     Produkt
    0.07
    𐌸
    0.06
    spiracy
    0.06
    Donald
    0.06
    Act Density 0.025%

    No Known Activations