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

    Neuronpedia

    INDEX
    Explanations

    questions, tests, answers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     চিন্ত
    0.48
     Elena
    0.46
    ⓞ
    0.46
    铄
    0.46
     Sarm
    0.43
     Mas
    0.40
    >
    0.40
    Elena
    0.40
    烷
    0.39
     നാല
    0.39
    POSITIVE LOGITS
    तालों
    0.46
     stadiums
    0.44
     pesta
    0.42
     sottop
    0.42
    ार्टम
    0.41
     terminated
    0.41
    द्य
    0.40
     regulated
    0.40
     franchises
    0.40
     клиентов
    0.40
    Act Density 0.002%

    No Known Activations