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

    Neuronpedia

    INDEX
    Explanations

    ening

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    must
    -0.07
     Grande
    -0.07
     important
    -0.07
     (:
    -0.06
    	glut
    -0.06
    monkey
    -0.06
    �
    -0.06
     molecules
    -0.06
     neighboring
    -0.06
    荬
    -0.06
    POSITIVE LOGITS
     desserts
    0.07
    eldig
    0.07
    moil
    0.07
    架构
    0.07
    年轻人
    0.07
    jącą
    0.07
    殡
    0.07
    ируют
    0.07
    resenter
    0.07
     العسكرية
    0.07
    Act Density 0.211%

    No Known Activations