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

    Neuronpedia

    INDEX
    Explanations

    hyp

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     redness
    0.74
     coni
    0.69
     stereo
    0.69
    ieuse
    0.68
    ेंट
    0.68
     RED
    0.67
     红
    0.66
    ত্রী
    0.66
    pflicht
    0.66
    紅
    0.65
    POSITIVE LOGITS
    Fixed
    0.67
    fixed
    0.67
     fixed
    0.62
    hea
    0.62
    Worldwide
    0.61
     Fixed
    0.60
    Per
    0.58
     তত্ব
    0.58
     FIXED
    0.58
    izontal
    0.57
    Act Density 0.009%

    No Known Activations