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

    Neuronpedia

    INDEX
    Explanations

    little women and little bunny

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rang
    0.83
    acle
    0.79
    ango
    0.69
    ran
    0.68
    anga
    0.68
     τ
    0.67
     elbow
    0.67
    ത്ര
    0.66
    Pag
    0.66
    Cab
    0.66
    POSITIVE LOGITS
     ঘো
    0.77
    インタ
    0.75
     साप्ताहिक
    0.72
     Baker
    0.72
     fondos
    0.69
    oyens
    0.67
     Boxes
    0.67
     inserir
    0.67
    ሾ
    0.67
    inent
    0.66
    Act Density 0.000%

    No Known Activations