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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Deliver
    -0.07
     specialties
    -0.06
    (component
    -0.06
     Contracts
    -0.06
     Subset
    -0.06
    isempty
    -0.06
     stage
    -0.06
     Supplements
    -0.06
     Recreation
    -0.06
     rout
    -0.06
    POSITIVE LOGITS
    .son
    0.07
    gregate
    0.06
     trh
    0.06
    oogle
    0.06
    Terr
    0.06
    idla
    0.06
     ['#
    0.06
    Winter
    0.06
     венти
    0.06
    صه
    0.06
    Act Density 0.099%

    No Known Activations