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

    Neuronpedia

    INDEX
    Explanations

    don't be, don't tell, don't expect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     physicist
    0.46
    pall
    0.46
    พบ
    0.43
     refuge
    0.43
     drawback
    0.42
     \
    0.42
     everywhere
    0.42
     physicists
    0.42
    ಕ್ಕು
    0.41
     subset
    0.41
    POSITIVE LOGITS
    či
    0.45
    ூரில்
    0.44
    وات
    0.40
    ným
    0.40
    nému
    0.39
    斯坦
    0.38
     б
    0.38
     де
    0.38
    НЕ
    0.38
     Transparency
    0.37
    Act Density 0.003%

    No Known Activations