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

    Neuronpedia

    INDEX
    Explanations

    flip and flips

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ラブ
    0.39
    गमेंट
    0.39
     andare
    0.38
    ì
    0.37
     Gül
    0.37
    ihara
    0.37
    incremental
    0.36
     আবশ্যক
    0.36
    жет
    0.36
    inergic
    0.36
    POSITIVE LOGITS
     flip
    1.34
     flips
    1.34
     flipping
    1.32
     flipped
    1.30
     Flip
    1.25
    Flip
    1.20
     Fli
    1.19
    翻
    1.17
    flip
    1.08
     फ्लिप
    1.05
    Act Density 0.003%

    No Known Activations