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

    Neuronpedia

    INDEX
    Explanations

    harmful pornography and behavior

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ácil
    0.46
    pm
    0.45
    2
    0.44
     stoichi
    0.44
    amsfonts
    0.44
     számos
    0.44
     outperforms
    0.43
    丁寧に
    0.43
    ro
    0.43
    brother
    0.42
    POSITIVE LOGITS
    是否
    0.87
    是否有
    0.83
    能否
    0.79
     whether
    0.74
    能不能
    0.73
    如何
    0.72
     是否
    0.69
    是否存在
    0.68
     suitability
    0.66
     విషయ
    0.65
    Act Density 0.108%

    No Known Activations