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

    Neuronpedia

    INDEX
    Explanations

    investigated

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Casual
    -0.07
    .hadoop
    -0.07
     мод
    -0.07
     treff
    -0.06
     Код
    -0.06
    navbarDropdown
    -0.06
     rims
    -0.06
    िथ
    -0.06
     많이
    -0.06
    oo
    -0.06
    POSITIVE LOGITS
     questioned
    0.07
    BJECT
    0.06
     Ack
    0.06
     Osman
    0.06
    응
    0.06
     věc
    0.06
     ISS
    0.06
     BMI
    0.06
    .Fire
    0.06
     luk
    0.06
    Act Density 0.020%

    No Known Activations