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

    Neuronpedia

    INDEX
    Explanations

    early return or exit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     immediately
    0.39
     aircraft
    0.39
     which
    0.38
     returns
    0.38
     Responsible
    0.37
    Responsible
    0.37
     Its
    0.36
     responsible
    0.36
     terminals
    0.36
     and
    0.36
    POSITIVE LOGITS
     স্বরে
    0.37
    ifdef
    0.35
    <div>
    0.34
     бойынша
    0.34
     Jeżeli
    0.34
    靔
    0.33
     छंद
    0.33
    팎
    0.33
     буенча
    0.33
    ləş
    0.32
    Act Density 0.000%

    No Known Activations