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
     Drake
    -0.06
     праців
    -0.06
     Perspectives
    -0.06
     発
    -0.06
    Extractor
    -0.06
     aer
    -0.06
     ions
    -0.06
    وية
    -0.06
     Unsure
    -0.06
    -video
    -0.06
    POSITIVE LOGITS
     sposób
    0.07
     Plays
    0.07
     ',',
    0.06
     Başkan
    0.06
     drib
    0.06
     důvodu
    0.06
    .val
    0.06
    ละคร
    0.06
     проц
    0.06
    _STAGE
    0.06
    Act Density 0.046%

    No Known Activations