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

    Neuronpedia

    INDEX
    Explanations

    good

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -label
    -0.07
    }/{
    -0.07
    су
    -0.06
    179
    -0.06
     unh
    -0.06
     تج
    -0.06
     MOST
    -0.06
    _dm
    -0.06
    -sample
    -0.06
    シェ
    -0.06
    POSITIVE LOGITS
     forwards
    0.07
     fungus
    0.07
     dernier
    0.07
    ioxid
    0.06
     createStore
    0.06
     good
    0.06
    iagnostics
    0.06
     parçası
    0.06
     reducer
    0.06
    Locator
    0.06
    Act Density 0.006%

    No Known Activations