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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uben
    -0.07
    _Msp
    -0.07
    (slice
    -0.07
     ngừng
    -0.07
    blast
    -0.07
    >An
    -0.07
     Toll
    -0.06
    壕
    -0.06
     Mercer
    -0.06
    izon
    -0.06
    POSITIVE LOGITS
    排出
    0.08
    iams
    0.07
    文化传播
    0.07
    )));↵↵
    0.07
    ชา
    0.07
    𝗘
    0.07
    キャンペーン
    0.06
    Coordinates
    0.06
    Pay
    0.06
     }}↵
    0.06
    Act Density 0.105%

    No Known Activations