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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ཁ
    -0.07
    ActionPerformed
    -0.07
    ḁ
    -0.07
     היא
    -0.06
     Nak
    -0.06
    当作
    -0.06
     collectionView
    -0.06
    ubyte
    -0.06
    -ms
    -0.06
     unsure
    -0.06
    POSITIVE LOGITS
     murders
    0.08
    办公楼
    0.07
    솊
    0.07
    \Migration
    0.07
    ORITY
    0.07
     voiture
    0.07
     union
    0.07
     parties
    0.07
     Recorder
    0.07
    рид
    0.07
    Act Density 0.003%

    No Known Activations