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

    Neuronpedia

    INDEX
    Explanations

    seat and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     FileNotFound
    0.88
     supprim
    0.87
     abandoned
    0.86
     sorun
    0.84
     imshow
    0.84
    问题
    0.81
     בז
    0.80
     байланы
    0.80
     વિદ્યાર્થી
    0.80
     いっ
    0.78
    POSITIVE LOGITS
    rell
    0.92
    Coffee
    0.79
    Caps
    0.78
    deload
    0.76
    boli
    0.76
     சற்று
    0.75
    fords
    0.74
    Cork
    0.74
     Lala
    0.73
    elbow
    0.72
    Act Density 0.000%

    No Known Activations