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

    Neuronpedia

    INDEX
    Explanations

    positive customer reviews

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hip
    -0.07
     norm
    -0.07
     preempt
    -0.06
     inclusion
    -0.06
    ία
    -0.06
    692
    -0.06
     Ivan
    -0.06
     stunt
    -0.06
     morality
    -0.06
     oriented
    -0.06
    POSITIVE LOGITS
    .getClassName
    0.07
    RestController
    0.06
     ----------↵
    0.06
    ゴリ
    0.06
    (uint
    0.06
    Rom
    0.06
    FILE
    0.06
     Kişisel
    0.06
     declining
    0.06
    坐在
    0.06
    Act Density 0.031%

    No Known Activations