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

    Neuronpedia

    INDEX
    Explanations

    verb conjugations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     |
↵
    -0.08
    ecedor
    -0.07
    ,
↵
    -0.07
    ↵
    -0.07
    	↵↵
    -0.07
    _EQUALS
    -0.07
    |
↵
    -0.07
    ?>"/>↵
    -0.07
    }];↵
    -0.06
    											↵
    -0.06
    POSITIVE LOGITS
    -speaking
    0.06
     payouts
    0.06
     bank
    0.06
    �
    0.06
     Aristotle
    0.06
     piston
    0.06
     presumed
    0.06
    ider
    0.06
    ummings
    0.06
     spoof
    0.06
    Act Density 0.429%

    No Known Activations