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

    Neuronpedia

    INDEX
    Explanations

    sports scores

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    หร
    -0.07
    ,ll
    -0.07
     má
    -0.07
     rb
    -0.06
    �
    -0.06
    better
    -0.06
    Ron
    -0.06
    each
    -0.06
    utils
    -0.06
     ​
    -0.06
    POSITIVE LOGITS
    _Application
    0.06
     BusinessException
    0.06
     viewType
    0.06
     routes
    0.06
     Sexy
    0.06
    stype
    0.06
    BMW
    0.06
     NET
    0.06
     nightmares
    0.06
     to
    0.06
    Act Density 0.004%

    No Known Activations