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

    Neuronpedia

    INDEX
    Explanations

    provides or generates items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }=
    0.20
    }=\
    0.20
     باستخدام
    0.18
     verwendeten
    0.17
     तुम्ही
    0.17
    itabbo
    0.17
     რომელი
    0.17
     của
    0.17
    ernacle
    0.17
    }-
    0.16
    POSITIVE LOGITS
     an
    0.34
     a
    0.31
     more
    0.24
     insights
    0.22
    A
    0.22
     một
    0.22
     некоторое
    0.22
     several
    0.22
     some
    0.21
     unui
    0.21
    Act Density 4.244%

    No Known Activations