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

    Neuronpedia

    INDEX
    Explanations

    time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bachelor
    -0.07
     Conveyor
    -0.07
     obr
    -0.07
     flotation
    -0.06
    verted
    -0.06
     sotto
    -0.06
    POSITORY
    -0.06
    lector
    -0.06
    conciliation
    -0.06
     Contractor
    -0.06
    POSITIVE LOGITS
    [^
    0.07
    .type
    0.07
     {[%
    0.06
     Boxing
    0.06
     believing
    0.06
    Marcus
    0.06
     Soup
    0.06
     guess
    0.06
     legally
    0.06
    (port
    0.06
    Act Density 0.005%

    No Known Activations