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

    Neuronpedia

    INDEX
    Explanations

    sleeve

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    69
    -0.07
    .'/'.$
    -0.07
    -radio
    -0.07
    _\
    -0.06
    174
    -0.06
    .ToBoolean
    -0.06
    ]],
    -0.06
     (...)
    -0.06
     trú
    -0.06
     ship
    -0.06
    POSITIVE LOGITS
     sleeve
    0.10
     sleeves
    0.08
     Sleeve
    0.08
     Slee
    0.07
    ween
    0.07
    iej
    0.07
    uppet
    0.06
    eltas
    0.06
    reed
    0.06
    cec
    0.06
    Act Density 0.003%

    No Known Activations