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

    Neuronpedia

    INDEX
    Explanations

    actions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    raisal
    -0.07
     hele
    -0.07
    Luke
    -0.06
    lay
    -0.06
    ｒ
    -0.06
     програ
    -0.06
     patrol
    -0.06
     ут
    -0.06
    LE
    -0.06
    ,↵↵
    -0.06
    POSITIVE LOGITS
     yıllık
    0.08
    的
    0.07
     based
    0.07
     的
    0.07
    .setAlignment
    0.07
    Rejected
    0.07
     Compatible
    0.06
     CHtml
    0.06
     Sql
    0.06
     akin
    0.06
    Act Density 0.110%

    No Known Activations