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

    Neuronpedia

    INDEX
    Explanations

    foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     centrally
    -0.07
     SD
    -0.07
     accommodation
    -0.06
     Lon
    -0.06
    35
    -0.06
     scalable
    -0.06
    110
    -0.06
    850
    -0.06
    938
    -0.06
     TOUCH
    -0.06
    POSITIVE LOGITS
     país
    0.07
    landa
    0.06
     consum
    0.06
     história
    0.06
    gy
    0.06
     chill
    0.06
    _offer
    0.06
     pís
    0.06
    yectos
    0.06
    増
    0.06
    Act Density 0.017%

    No Known Activations