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

    Neuronpedia

    INDEX
    Explanations

    connection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     weiß
    -0.06
    widgets
    -0.06
     králov
    -0.06
     phoneNumber
    -0.06
    _dtype
    -0.06
     traumatic
    -0.06
     [:
    -0.06
    (weather
    -0.06
    жения
    -0.06
    ('${
    -0.06
    POSITIVE LOGITS
     اصفهان
    0.07
    潜
    0.06
    _ij
    0.06
     �
    0.06
    .Views
    0.06
     evasion
    0.06
     Basement
    0.06
    悲
    0.06
    ercul
    0.06
    verture
    0.06
    Act Density 0.000%

    No Known Activations