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

    Neuronpedia

    INDEX
    Explanations

    pick-up lines or rhetorical questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ，
    1.22
     ,
    1.21
     ايضا
    1.08
     ،
    1.06
     ।
    0.99
     そして
    0.94
     These
    0.94
     aceste
    0.93
     acest
    0.92
     وهذا
    0.91
    POSITIVE LOGITS
     Poké
    0.93
     ridiculous
    0.73
    MDEwOlJlcG
    0.72
    DetailUI
    0.71
     DirectX
    0.69
    <unused9>
    0.68
     blatantly
    0.67
     :/
    0.67
     Pokémon
    0.66
     offseason
    0.66
    Act Density 0.036%

    No Known Activations