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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     basics
    -0.07
     Bark
    -0.06
    OWER
    -0.06
    opal
    -0.06
     bulunduğu
    -0.06
    นๆ
    -0.06
    會
    -0.06
     Hal
    -0.06
    しか
    -0.06
    /cart
    -0.06
    POSITIVE LOGITS
    issor
    0.07
    ='${
    0.06
    -cent
    0.06
    )((((
    0.06
     Recorder
    0.06
     algum
    0.06
    �
    0.06
    console
    0.06
    zept
    0.06
     чув
    0.06
    Act Density 0.027%

    No Known Activations