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

    Neuronpedia

    INDEX
    Explanations

    ummer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     responder
    -0.08
     chưa
    -0.08
     shimmering
    -0.08
    ю
    -0.07
     flaky
    -0.07
     отвеч
    -0.07
     отвечает
    -0.07
    кла
    -0.07
     responds
    -0.07
     responders
    -0.07
    POSITIVE LOGITS
    expr
    0.09
    atm
    0.09
    haid
    0.08
    Paragraph
    0.08
     Contract
    0.08
     Universidad
    0.08
     Barcel
    0.07
    atorium
    0.07
     Avenida
    0.07
    ാളെ
    0.07
    Act Density 0.000%

    No Known Activations