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

    Neuronpedia

    INDEX
    Explanations

    play rock

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ());
    0.34
     powodu
    0.30
     هستند
    0.30
     ممکن
    0.30
     !=
    0.30
     mức
    0.29
     obwohl
    0.29
     multiplied
    0.29
    PARATION
    0.29
     /=
    0.28
    POSITIVE LOGITS
     your
    0.46
     them
    0.44
     the
    0.43
     their
    0.39
     our
    0.39
    ਾ
    0.37
     its
    0.37
     ও
    0.35
    和
    0.35
     his
    0.35
    Act Density 0.531%

    No Known Activations