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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    4
    0.85
    ４
    0.84
     ۴
    0.84
    ⁴
    0.82
     ५
    0.81
    ៤
    0.81
     ৪
    0.81
     ४
    0.80
     ৫০
    0.78
     fift
    0.77
    POSITIVE LOGITS
     കോടതി
    0.70
    致します
    0.69
     fast
    0.68
    𝟮
    0.68
     Bush
    0.67
    следования
    0.65
    രുത്
    0.64
    ૨
    0.62
     Rothschild
    0.61
    ೨
    0.61
    Act Density 0.006%

    No Known Activations