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

    Neuronpedia

    INDEX
    Explanations

    catching

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Gravity
    -0.07
     bara
    -0.06
    (root
    -0.06
     chiếu
    -0.06
     Kov
    -0.06
    FIXME
    -0.06
     transforming
    -0.06
    .Out
    -0.06
    ElementException
    -0.06
    ülü
    -0.06
    POSITIVE LOGITS
    -catching
    0.11
     catchy
    0.10
     tasty
    0.07
     tempting
    0.06
    )!↵
    0.06
    breaking
    0.06
    !";
↵
    0.06
    ुझ
    0.06
     bitter
    0.06
    인의
    0.06
    Act Density 0.002%

    No Known Activations