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

    Neuronpedia

    INDEX
    Explanations

    Period token

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    、三
    -0.07
    _WRAPPER
    -0.06
    etu
    -0.06
     contrario
    -0.06
    iado
    -0.06
    	usage
    -0.06
     serv
    -0.06
     Feb
    -0.06
     "}
    -0.06
     tandem
    -0.06
    POSITIVE LOGITS
     увер
    0.07
     friend
    0.07
    _cores
    0.07
    Extras
    0.07
    ंटर
    0.06
     Δημο
    0.06
    rotein
    0.06
    spirit
    0.06
    _PREFIX
    0.06
    �
    0.06
    Act Density 0.010%

    No Known Activations