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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Recording
    -0.08
     Overwatch
    -0.08
    اص
    -0.07
    NotAllowed
    -0.07
    _android
    -0.06
     pup
    -0.06
    Lifetime
    -0.06
    phase
    -0.06
    lastic
    -0.06
    Descriptions
    -0.06
    POSITIVE LOGITS
     smith
    0.07
     FBI
    0.07
     وصل
    0.06
     uměl
    0.06
     recebe
    0.06
    Years
    0.06
     perc
    0.06
    isher
    0.06
    xCF
    0.06
     ='
    0.06
    Act Density 0.082%

    No Known Activations