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

    Neuronpedia

    INDEX
    Explanations

    limited comparison

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    暏
    0.49
    🅔
    0.46
     unrivalled
    0.45
     WITHOUT
    0.45
    नांतर
    0.44
     اللّه
    0.43
    毫无
    0.43
    Without
    0.43
    ട്ടുണ്ട്
    0.43
     দেখিলাম
    0.43
    POSITIVE LOGITS
     compared
    0.90
    compared
    0.79
     Compared
    0.69
    それでも
    0.67
     (<
    0.66
     limited
    0.64
    Compared
    0.64
     dibandingkan
    0.62
     comparatively
    0.61
     محدود
    0.60
    Act Density 0.201%

    No Known Activations