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

    Neuronpedia

    INDEX
    Explanations

    fictional narrative

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     armies
    -0.08
     kra
    -0.07
    //↵
    -0.07
     particip
    -0.07
     outrage
    -0.06
     streaming
    -0.06
    atch
    -0.06
     Kra
    -0.06
     debate
    -0.06
     flown
    -0.06
    POSITIVE LOGITS
     біля
    0.07
    ��
    0.06
    ويك
    0.06
     그가
    0.06
    .neighbors
    0.06
     vue
    0.06
     تصمیم
    0.06
    _WIN
    0.06
    _BROWSER
    0.06
    _PARENT
    0.06
    Act Density 0.011%

    No Known Activations