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

    Neuronpedia

    INDEX
    Explanations

    operations to finish

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (?)
    0.75
    (?)
    0.74
     Explos
    0.74
    갤럭
    0.73
     கொண்டது
    0.72
    <unused527>
    0.72
     возмо
    0.71
    (!)
    0.70
    웅
    0.70
     পদ্ধ
    0.66
    POSITIVE LOGITS
     asimismo
    0.84
     dependability
    0.83
    ້າ
    0.76
     cops
    0.75
     renewables
    0.71
    <unused63>
    0.68
     gafas
    0.68
    ySpeed
    0.66
    again
    0.66
     uncomplicated
    0.66
    Act Density 9.477%

    No Known Activations