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

    Neuronpedia

    INDEX
    Explanations

    here's a breakdown

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     కొన్ని
    0.92
    いくつかの
    0.87
     কিছু
    0.84
     சில
    0.84
     some
    0.84
     بعض
    0.82
     algunas
    0.81
     Some
    0.80
     algunos
    0.80
     qualche
    0.79
    POSITIVE LOGITS
     같습니다
    0.95
     differentiates
    0.83
    rectangle
    0.82
     centralization
    0.82
     SCD
    0.82
     governs
    0.82
     같아요
    0.81
     Holistic
    0.81
    📉
    0.79
    ុល
    0.79
    Act Density 0.138%

    No Known Activations