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

    Neuronpedia

    INDEX
    Explanations

    look up details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    inery
    0.39
     bord
    0.38
    USION
    0.34
    avour
    0.33
    onic
    0.33
     bords
    0.33
     oportunidad
    0.32
     heterod
    0.32
     mussels
    0.32
    StdHandle
    0.32
    POSITIVE LOGITS
    <0x80>
    0.38
    惊
    0.33
     Př
    0.32
    叙
    0.32
    ▂
    0.32
     ​
    0.32
     Còn
    0.32
     Dear
    0.31
    ána
    0.31
     وزير
    0.30
    Act Density 0.002%

    No Known Activations