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

    Neuronpedia

    INDEX
    Explanations

    online/electronic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bez
    -0.06
     Felix
    -0.06
     dma
    -0.06
     Twe
    -0.06
    Px
    -0.06
     forgotten
    -0.06
    liquid
    -0.06
     Rachel
    -0.06
     rabbit
    -0.06
     repeatedly
    -0.06
    POSITIVE LOGITS
     �
    0.07
    ابان
    0.06
    λία
    0.06
     illusion
    0.06
    pragma
    0.06
    ющая
    0.06
     sessiz
    0.06
    _mgr
    0.06
     εμφ
    0.06
    #endif
    0.06
    Act Density 0.074%

    No Known Activations