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

    Neuronpedia

    INDEX
    Explanations

    parenthesis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [row
    -0.08
    Ϭ
    -0.07
    (date
    -0.07
     breathe
    -0.07
     steer
    -0.07
    _remain
    -0.06
     السعودي
    -0.06
    (unique
    -0.06
    土豪
    -0.06
    دافع
    -0.06
    POSITIVE LOGITS
    			↵
    0.07
    _ABI
    0.07
     Arizona
    0.07
     Banana
    0.06
    .va
    0.06
    Firefox
    0.06
     {}.
    0.06
     clusters
    0.06
    应用场景
    0.06
    毗
    0.06
    Act Density 0.000%

    No Known Activations