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

    Neuronpedia

    INDEX
    Explanations

    list items and code formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    0.43
    this
    0.43
    ;
    0.39
     Mt
    0.35
     this
    0.35
    =>
    0.35
    and
    0.34
     and
    0.34
    due
    0.34
    sthe
    0.34
    POSITIVE LOGITS
     też
    0.41
     sélectionnés
    0.41
     ၂
    0.41
    ၂
    0.39
    č
    0.39
     অন্যান্য
    0.38
    ávez
    0.38
     recuperación
    0.38
    unjungi
    0.38
     použ
    0.37
    Act Density 2.646%

    No Known Activations