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

    Neuronpedia

    INDEX
    Explanations

    randomness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    蕖
    0.92
    geq
    0.86
    ﻞ
    0.84
    ្នក
    0.81
    σαν
    0.79
    Autowired
    0.79
    thood
    0.78
    parseDouble
    0.77
    oC
    0.77
     pesky
    0.77
    POSITIVE LOGITS
    ের
    0.81
    ﻯ
    0.78
     creer
    0.78
    BUL
    0.71
    ли
    0.71
    Почему
    0.66
     terrain
    0.66
    ০০
    0.66
    chance
    0.65
    ча
    0.65
    Act Density 0.173%

    No Known Activations