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

    Neuronpedia

    INDEX
    Explanations

    Python code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    adopt
    -0.07
     usher
    -0.06
    finished
    -0.06
     entertained
    -0.06
    戏
    -0.06
     passes
    -0.06
     робіт
    -0.06
     wrapped
    -0.06
    ()))↵
    -0.06
    birds
    -0.06
    POSITIVE LOGITS
     Functional
    0.06
    <html
    0.06
    관리자
    0.06
     канди
    0.06
     Trigger
    0.06
    Tahoma
    0.06
     Carry
    0.06
    .sendStatus
    0.06
     PartialView
    0.06
     предполаг
    0.06
    Act Density 0.026%

    No Known Activations