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

    Neuronpedia

    INDEX
    Explanations

    professionals, auxiliaries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     overtime
    0.73
     rosa
    0.67
     silver
    0.66
     istek
    0.64
    ক্কা
    0.63
     uner
    0.63
     mineral
    0.63
    며
    0.62
     plate
    0.62
     pon
    0.62
    POSITIVE LOGITS
    IIT
    0.79
     പറ്റ
    0.76
     Tutor
    0.75
     Docs
    0.75
     Teaching
    0.74
    ভালোবাস
    0.73
     ਵਿੱਚ
    0.71
    Ꮀ
    0.71
    ﹚
    0.70
     Ghar
    0.70
    Act Density 0.000%

    No Known Activations