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

    Neuronpedia

    INDEX
    Explanations

    purification/quality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sangat
    -0.07
     المف
    -0.06
    $"
    -0.06
     Airlines
    -0.06
    (solution
    -0.06
     будів
    -0.06
    phia
    -0.06
     Exact
    -0.06
    FAIL
    -0.06
     Sở
    -0.06
    POSITIVE LOGITS
     beast
    0.07
     λο
    0.07
     lore
    0.07
     contro
    0.06
    _ipv
    0.06
    орт
    0.06
     ابت
    0.06
    _D
    0.06
     viewing
    0.06
     wiping
    0.06
    Act Density 0.020%

    No Known Activations