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

    Neuronpedia

    INDEX
    Explanations

    Fibonacci sequence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    蹚
    -0.07
    囔
    -0.07
    以习近平
    -0.07
    _Tool
    -0.07
    韭菜
    -0.06
    Hp
    -0.06
    _yes
    -0.06
    ˘
    -0.06
    西班
    -0.06
    onomy
    -0.06
    POSITIVE LOGITS
     harassment
    0.07
     Len
    0.07
     Disorder
    0.07
    事故发生
    0.07
    _frame
    0.07
    EQUAL
    0.06
    _od
    0.06
     overlook
    0.06
     transform
    0.06
     ELECT
    0.06
    Act Density 0.013%

    No Known Activations