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

    Neuronpedia

    INDEX
    Explanations

    comparisons and degrees

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     New
    0.49
     leadership
    0.47
     outright
    0.44
     dance
    0.44
     told
    0.43
     windows
    0.43
     erection
    0.43
    ed
    0.43
     growth
    0.43
    alls
    0.42
    POSITIVE LOGITS
     ਯ
    0.51
    uée
    0.49
     एससी
    0.47
     conteúdos
    0.46
     ООО
    0.46
     இப்போது
    0.46
    見える
    0.45
    ль
    0.44
    𝘪
    0.44
     quieran
    0.43
    Act Density 0.002%

    No Known Activations