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

    Neuronpedia

    INDEX
    Explanations

    items or units

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ovanie
    0.77
    eliness
    0.77
    jasmine
    0.71
    惕
    0.69
     новий
    0.69
     大きい
    0.69
    Khan
    0.69
    ःख
    0.68
     hendak
    0.68
     związane
    0.68
    POSITIVE LOGITS
     moneda
    0.82
     memoranda
    0.79
     HAL
    0.79
     pencils
    0.77
     centerpiece
    0.76
     E
    0.75
     turbines
    0.75
     centerline
    0.74
     fertilizers
    0.73
     refills
    0.73
    Act Density 0.000%

    No Known Activations