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

    Neuronpedia

    INDEX
    Explanations

    family dynamic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     எல்லை
    0.44
     akhir
    0.41
     medalist
    0.41
     scrapbook
    0.40
    ısında
    0.40
     Bhagava
    0.39
     제곱
    0.39
     candle
    0.39
     إِل
    0.39
    Ꮜ
    0.39
    POSITIVE LOGITS
    Cloud
    0.57
     Cloud
    0.57
     cloud
    0.56
    cloud
    0.53
    云
    0.53
    雲
    0.53
     clouds
    0.51
     clinical
    0.50
     Clouds
    0.50
     Clarke
    0.50
    Act Density 0.000%

    No Known Activations