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

    Neuronpedia

    INDEX
    Explanations

    MDN meta tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Lösung
    0.60
    으
    0.59
    뷁
    0.58
     "*
    0.58
    \$
    0.57
    ěz
    0.57
    "*
    0.56
     alturas
    0.56
    츠
    0.55
    ថា
    0.55
    POSITIVE LOGITS
     pour
    0.82
     pouring
    0.78
     vivre
    0.76
     ঠান্ডা
    0.75
     falling
    0.73
     نوا
    0.72
     Slov
    0.72
     accumulate
    0.72
     meditate
    0.72
     configure
    0.70
    Act Density 0.007%

    No Known Activations