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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
     ferr
    -0.07
    Men
    -0.06
     Eh
    -0.06
    >$
    -0.06
     Men
    -0.06
    Exc
    -0.06
     云
    -0.06
     Mc
    -0.06
    $c
    -0.06
    POSITIVE LOGITS
     соедин
    0.07
    法
    0.07
    лий
    0.07
    posal
    0.07
     Seriously
    0.06
     jako
    0.06
    UIAlertAction
    0.06
    истра
    0.06
    ingular
    0.06
     Bike
    0.06
    Act Density 0.002%

    No Known Activations