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

    Neuronpedia

    INDEX
    Explanations

    list factors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.48
    ن
    0.48
    r
    0.46
    -
    0.46
    ката
    0.44
    و
    0.43
    வதில்
    0.43
    می
    0.43
     opportunity
    0.42
    ని
    0.42
    POSITIVE LOGITS
     ቦ
    0.50
    မဟုတ်
    0.49
     හෝ
    0.47
     దూర
    0.44
    ចាយ
    0.44
     పెరుగు
    0.43
    ัติ
    0.43
     demain
    0.43
     দক্ষিণে
    0.42
     ಯ
    0.42
    Act Density 0.002%

    No Known Activations