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

    Neuronpedia

    INDEX
    Explanations

    #

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cultivated
    -0.07
     starttime
    -0.07
    842
    -0.07
     wounds
    -0.06
     þ
    -0.06
     widow
    -0.06
    े।
    -0.06
     weeds
    -0.06
     drift
    -0.06
     karar
    -0.06
    POSITIVE LOGITS
     inset
    0.06
    لك
    0.06
    \File
    0.06
     villages
    0.06
    ercul
    0.06
     teaspoons
    0.06
    ONGODB
    0.06
    -wow
    0.06
    -pre
    0.06
    생님
    0.06
    Act Density 0.003%

    No Known Activations