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

    Neuronpedia

    INDEX
    Explanations

    Code and XML

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	slot
    -0.08
     Kepler
    -0.07
    Lights
    -0.07
     ${↵
    -0.07
    ��
    -0.06
    ителем
    -0.06
    amburg
    -0.06
    aty
    -0.06
     pracy
    -0.06
    ojí
    -0.06
    POSITIVE LOGITS
    &);↵
    0.07
    ACHE
    0.06
     ERROR
    0.06
    /time
    0.06
     Scale
    0.06
     Helm
    0.06
     DEC
    0.06
    did
    0.06
    бе
    0.06
    Did
    0.06
    Act Density 0.020%

    No Known Activations