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

    Neuronpedia

    INDEX
    Explanations

    n

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    irler
    -0.07
     frem
    -0.07
    >Main
    -0.07
     základě
    -0.07
    uper
    -0.07
     Leslie
    -0.07
     ocas
    -0.07
    Pay
    -0.06
     leasing
    -0.06
     chanting
    -0.06
    POSITIVE LOGITS
    nement
    0.06
    -term
    0.06
    national
    0.06
    اگ
    0.06
    .shortcuts
    0.06
    argo
    0.05
     casting
    0.05
    約
    0.05
    bled
    0.05
     invention
    0.05
    Act Density 0.020%

    No Known Activations