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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     words
    -0.06
    ět
    -0.06
     свящ
    -0.06
     váž
    -0.06
     |[
    -0.06
    .Predicate
    -0.06
     cosm
    -0.06
     unnatural
    -0.06
    graphic
    -0.06
    ौकर
    -0.06
    POSITIVE LOGITS
     Deployment
    0.07
     struggling
    0.07
     accomplished
    0.07
     يناير
    0.06
    ardown
    0.06
    _av
    0.06
    .onActivityResult
    0.06
    도
    0.06
     episode
    0.06
    Separator
    0.06
    Act Density 0.001%

    No Known Activations