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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    haul
    -0.07
    кап
    -0.06
     mn
    -0.06
    trail
    -0.06
     стран
    -0.06
     Pháp
    -0.06
    AAA
    -0.06
    —or
    -0.06
     Huffington
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     WITH
    0.07
     Chung
    0.07
     behold
    0.07
     крит
    0.07
    QWidget
    0.07
     flexDirection
    0.07
    Lint
    0.06
    _MESSAGES
    0.06
     enviado
    0.06
    .Uri
    0.06
    Act Density 0.048%

    No Known Activations