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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _const
    -0.06
    Jack
    -0.06
    LY
    -0.06
     Raphael
    -0.06
     Lowell
    -0.06
     Jack
    -0.06
     DEAL
    -0.06
    ickey
    -0.06
    ancies
    -0.06
    esty
    -0.06
    POSITIVE LOGITS
     Пр
    0.07
     biking
    0.06
    	fd
    0.06
     agosto
    0.06
     непосред
    0.06
    \Module
    0.06
     convention
    0.06
     музы
    0.06
     план
    0.06
    .BO
    0.06
    Act Density 0.019%

    No Known Activations