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

    Neuronpedia

    INDEX
    Explanations

    File paths/names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Failure
    -0.07
    感冒
    -0.07
    暮
    -0.07
    端午
    -0.07
    ansible
    -0.07
    بريد
    -0.07
     numb
    -0.07
    unicip
    -0.07
     Liqu
    -0.07
     satin
    -0.07
    POSITIVE LOGITS
     HOST
    0.07
     Layer
    0.07
     """↵↵
    0.07
    UnityEngine
    0.06
    约谈
    0.06
     cuatro
    0.06
     כל
    0.06
    dojo
    0.06
    打造
    0.06
     */
↵
↵
    0.06
    Act Density 0.001%

    No Known Activations