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

    Neuronpedia

    INDEX
    Explanations

    equivalent to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     necessities
    0.46
     chó
    0.44
     য
    0.42
     kisses
    0.41
    Carrier
    0.41
    Cookie
    0.40
     coat
    0.40
    Coat
    0.40
     ;
    0.39
     errands
    0.39
    POSITIVE LOGITS
     tomonidan
    0.46
     Canonical
    0.45
    ்துறை
    0.44
     yönelik
    0.44
     शिवसेने
    0.43
     درسنا
    0.42
    aremos
    0.40
    ujeme
    0.40
     Uhuru
    0.40
     நடத்திய
    0.39
    Act Density 0.004%

    No Known Activations