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

    Neuronpedia

    INDEX
    Explanations

    limitations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     мм
    -0.08
     directed
    -0.07
     interact
    -0.07
     日期
    -0.07
    ')
    -0.07
    計劃
    -0.07
    La
    -0.06
    計
    -0.06
    '))
    -0.06
    (currency
    -0.06
    POSITIVE LOGITS
    tournament
    0.07
     enfermed
    0.06
    .toastr
    0.06
     Encode
    0.06
     smoothly
    0.06
    pose
    0.06
     औ
    0.06
     прост
    0.06
     nhẹ
    0.06
    temp
    0.06
    Act Density 0.056%

    No Known Activations