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

    Neuronpedia

    INDEX
    Explanations

    explanation about history or facts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ঘৃণা
    0.68
    ᅦ
    0.67
    ্বিত
    0.66
    禽
    0.65
     Кей
    0.65
    ሒ
    0.65
     Primera
    0.64
     Buenas
    0.64
    стая
    0.64
     clums
    0.63
    POSITIVE LOGITS
    राधना
    0.76
    Tables
    0.76
     dagli
    0.76
     dosen
    0.74
     ses
    0.74
    iora
    0.74
    ec
    0.73
     টেব
    0.73
    いない
    0.72
     Hickman
    0.71
    Act Density 0.003%

    No Known Activations