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

    Neuronpedia

    INDEX
    Explanations

    priority and yielding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     takes
    1.34
    takes
    1.23
     Takes
    1.17
    Take
    1.16
    Takes
    1.16
     take
    1.16
    take
    1.12
     Take
    1.09
     TAKE
    1.05
     precedence
    1.04
    POSITIVE LOGITS
     Nev
    0.40
     nev
    0.40
     nan
    0.39
     Nan
    0.39
     nanom
    0.38
     śnie
    0.36
     atmosfer
    0.35
    设
    0.35
    Nan
    0.35
    Насе
    0.35
    Act Density 0.003%

    No Known Activations