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

    Neuronpedia

    INDEX
    Explanations

    suffixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "f
    -0.07
     humanities
    -0.07
    לם
    -0.06
     Eng
    -0.06
    ∼
    -0.06
    議
    -0.06
    _syntax
    -0.06
    ckpt
    -0.06
    一首
    -0.06
    .Parameter
    -0.06
    POSITIVE LOGITS
     slots
    0.07
     jak
    0.07
    .sal
    0.07
     Pregnancy
    0.07
     المزيد
    0.06
    Actions
    0.06
    |unique
    0.06
    .ALIGN
    0.06
    fur
    0.06
    成功的
    0.06
    Act Density 0.027%

    No Known Activations