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

    Neuronpedia

    INDEX
    Explanations

    floors and levels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Server
    0.61
     Propulsion
    0.57
    herent
    0.54
    하십시오
    0.53
     Imagery
    0.52
    uelo
    0.52
    繁殖
    0.52
    uminous
    0.51
    伎
    0.51
     До
    0.50
    POSITIVE LOGITS
     lakini
    0.64
     perceived
    0.57
    ͜
    0.56
     opacity
    0.55
    次
    0.54
     biggest
    0.53
    يع
    0.53
     някои
    0.53
     opinião
    0.52
     kaca
    0.52
    Act Density 0.001%

    No Known Activations