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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    링
    -0.07
    >().
    -0.06
    \Desktop
    -0.06
     BOX
    -0.06
    CKET
    -0.06
    link
    -0.06
    Container
    -0.06
     товар
    -0.06
    atica
    -0.06
    :host
    -0.06
    POSITIVE LOGITS
    Illegal
    0.07
    corner
    0.06
    Emb
    0.06
    Nich
    0.06
    Пер
    0.06
     rises
    0.06
     legitimate
    0.06
     вклад
    0.06
     друж
    0.06
     permitted
    0.06
    Act Density 0.001%

    No Known Activations