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

    Neuronpedia

    INDEX
    Explanations

    time units and approximations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Selle
    0.84
     ħ
    0.81
     לא
    0.81
    👏👏👏👏
    0.80
     навчання
    0.80
    urée
    0.80
    =========
    0.79
    গ্রেস
    0.79
    ServiceGroupID
    0.79
    épendant
    0.79
    POSITIVE LOGITS
    or
    1.12
     or
    1.09
     dozen
    1.04
     couple
    0.92
     ish
    0.91
    または
    0.90
    (?)
    0.87
     sorts
    0.84
     или
    0.84
     roughly
    0.83
    Act Density 0.038%

    No Known Activations