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

    Neuronpedia

    INDEX
    Explanations

    setting environment variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    decomposition
    0.42
    releases
    0.40
    agiarism
    0.39
     nCmdShow
    0.37
    semp
    0.35
     कमांड
    0.35
    remove
    0.34
    Short
    0.34
    ldots
    0.33
    shoot
    0.33
    POSITIVE LOGITS
     settings
    0.51
     destin
    0.46
     object
    0.43
     subiect
    0.43
     belonged
    0.41
     sasan
    0.41
     объекта
    0.41
     ঘটেছে
    0.40
     subject
    0.40
     bearers
    0.40
    Act Density 0.000%

    No Known Activations