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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Attribution
    -0.06
     clockwise
    -0.06
     lotion
    -0.06
    bidden
    -0.06
    .PNG
    -0.06
     полов
    -0.06
    ANEL
    -0.06
    بد
    -0.06
    вание
    -0.06
    wards
    -0.06
    POSITIVE LOGITS
    Del
    0.07
    рех
    0.06
    Tro
    0.06
     Compass
    0.06
     datas
    0.06
    于是
    0.06
     LIS
    0.06
     ka
    0.06
    مق
    0.06
    	dev
    0.05
    Act Density 0.000%

    No Known Activations