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

    Neuronpedia

    INDEX
    Explanations

    explaining meaning or how

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    0.43
     B
    0.38
    .]
    0.38
     Magnet
    0.38
     Ayrıca
    0.38
     Mol
    0.36
     :
    0.36
    也很
    0.35
     Cal
    0.35
     Sp
    0.35
    POSITIVE LOGITS
     cioè
    0.49
    あなたが
    0.42
    㓡
    0.41
    tidak
    0.40
    ğin
    0.40
     איך
    0.39
     тобто
    0.39
    जहां
    0.38
     آنچه
    0.38
    डून
    0.38
    Act Density 0.775%

    No Known Activations