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

    Neuronpedia

    INDEX
    Explanations

    rotation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    湾
    -0.07
     welt
    -0.07
    .machine
    -0.07
     powered
    -0.07
    рам
    -0.07
     penalties
    -0.06
     meals
    -0.06
    -powered
    -0.06
     ly
    -0.06
    級
    -0.06
    POSITIVE LOGITS
     poultry
    0.07
    likle
    0.06
     formulario
    0.06
     что
    0.06
    quiz
    0.06
     Snowden
    0.06
    ैं.↵
    0.06
     Wilderness
    0.06
    ELLOW
    0.06
     reck
    0.06
    Act Density 0.012%

    No Known Activations