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

    Neuronpedia

    INDEX
    Explanations

    programming actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     phénomènes
    0.35
     compreender
    0.35
     imassa
    0.34
    茁
    0.33
    蓊
    0.33
    squarePos
    0.33
     ມີ
    0.33
     бывают
    0.32
     постепен
    0.32
    境界層
    0.32
    POSITIVE LOGITS
     create
    0.63
     add
    0.60
     creates
    0.60
     specify
    0.60
     creating
    0.59
     obtain
    0.58
     send
    0.57
     initialize
    0.57
     assigning
    0.56
     activate
    0.55
    Act Density 0.167%

    No Known Activations