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

    Neuronpedia

    INDEX
    Explanations

    ` = { `

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    myCollision
    0.50
     其中
    0.46
     Bhagava
    0.45
     വേണ്ടി
    0.44
     Braunsch
    0.43
    americanos
    0.42
    先生
    0.41
    rdquo
    0.41
     ঘোষনা
    0.41
     ListTile
    0.41
    POSITIVE LOGITS
     generations
    0.52
     lumin
    0.40
    ক্তির
    0.40
     pan
    0.39
     lia
    0.39
    bek
    0.39
     Etern
    0.39
     scholars
    0.38
    ilib
    0.38
     etern
    0.38
    Act Density 0.000%

    No Known Activations