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

    Neuronpedia

    INDEX
    Explanations

    contraction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vídeos
    -0.07
     upro
    -0.07
    ]]=
    -0.07
    angepicker
    -0.06
     ISIL
    -0.06
     Країна
    -0.06
    _lit
    -0.06
     +#+
    -0.06
     FileAccess
    -0.06
    .DialogInterface
    -0.06
    POSITIVE LOGITS
     Automotive
    0.07
    SOR
    0.06
    老
    0.06
    CLE
    0.06
    rowning
    0.06
    ANTED
    0.06
    اون
    0.06
    实在
    0.06
     produk
    0.06
    _twitter
    0.06
    Act Density 0.000%

    No Known Activations