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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SB
    -0.08
    {x
    -0.08
     Pocket
    -0.07
    で
    -0.07
    theta
    -0.06
     gritty
    -0.06
     κατα
    -0.06
     ブ
    -0.06
     ราย
    -0.06
     Tax
    -0.06
    POSITIVE LOGITS
    .Alignment
    0.06
    .Fill
    0.06
    (remove
    0.06
     TableCell
    0.06
    ()↵
    0.06
     стра
    0.06
    etik
    0.06
    зн
    0.06
    using
    0.06
    ��
    0.06
    Act Density 0.016%

    No Known Activations