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

    Neuronpedia

    INDEX
    Explanations

    approximations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     clone
    -0.07
     همین
    -0.06
     элемент
    -0.06
     Си
    -0.06
    prung
    -0.06
     पश
    -0.06
    令
    -0.06
     спир
    -0.06
    _weather
    -0.06
     Brunswick
    -0.06
    POSITIVE LOGITS
    859
    0.07
    0.06
    [js
    0.06
     Coupe
    0.06
    tenant
    0.06
     agreements
    0.06
    .^
    0.06
    amily
    0.06
    _RESULTS
    0.06
     snapping
    0.06
    Act Density 0.020%

    No Known Activations