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

    Neuronpedia

    INDEX
    Explanations

    election years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    та
    0.84
    𝚗
    0.82
    ctive
    0.78
    க்கார
    0.78
    Cada
    0.73
     već
    0.72
     ни
    0.69
    Ahora
    0.69
     मुश्किल
    0.69
    {
    0.69
    POSITIVE LOGITS
    Попис
    0.88
     hereof
    0.84
     permittivity
    0.83
    surgeon
    0.83
    ዌ
    0.82
     economists
    0.82
    ngModel
    0.81
     emeritus
    0.81
     strangers
    0.80
     glimpses
    0.80
    Act Density 0.006%

    No Known Activations