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

    Neuronpedia

    INDEX
    Explanations

    install

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    YES
    -0.07
    ENDED
    -0.07
    ,axis
    -0.07
    asier
    -0.07
    	win
    -0.07
     colorWithRed
    -0.07
    97
    -0.07
    Join
    -0.07
    АН
    -0.07
    алю
    -0.07
    POSITIVE LOGITS
     Peg
    0.08
    //}}
    0.07
     λίγ
    0.06
     Adopt
    0.06
     công
    0.06
     plut
    0.06
     fight
    0.06
     decent
    0.06
     Ticket
    0.06
    적인
    0.06
    Act Density 0.002%

    No Known Activations