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

    Neuronpedia

    INDEX
    Explanations

    business summaries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tx
    -0.07
     dis
    -0.06
    WindowText
    -0.06
     должны
    -0.06
     assumed
    -0.06
    qi
    -0.06
    iPhone
    -0.06
    61
    -0.06
    Feel
    -0.06
    cost
    -0.06
    POSITIVE LOGITS
     Salary
    0.08
     mixins
    0.07
    /action
    0.07
     +++
    0.06
    Salary
    0.06
     khối
    0.06
    /")
    0.06
    rå
    0.06
    /de
    0.06
    INGS
    0.06
    Act Density 0.043%

    No Known Activations