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

    Neuronpedia

    INDEX
    Explanations

    comparing qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     مسؤول
    0.75
     Merit
    0.71
     आणखी
    0.64
     நூல்
    0.63
    zial
    0.63
    諱
    0.63
     orada
    0.62
    apses
    0.62
     değiş
    0.61
    ∅
    0.61
    POSITIVE LOGITS
     compared
    5.19
    compared
    4.82
     Compared
    4.56
    Compared
    4.32
     compare
    3.75
     dibandingkan
    3.71
     сравнению
    3.61
     compares
    3.49
     comparison
    3.39
    Compare
    3.33
    Act Density 0.411%

    No Known Activations