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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sns
    -0.07
     youths
    -0.06
     axes
    -0.06
    ucky
    -0.06
    .stdout
    -0.06
     Keto
    -0.06
     seasons
    -0.06
     shin
    -0.06
     deltas
    -0.06
    ierre
    -0.06
    POSITIVE LOGITS
     بلند
    0.07
    stripe
    0.07
     vývoj
    0.07
     interoper
    0.06
    _refptr
    0.06
     vẫn
    0.06
     Miracle
    0.06
    ثر
    0.06
     trường
    0.06
     사람들이
    0.06
    Act Density 0.000%

    No Known Activations