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

    Neuronpedia

    INDEX
    Explanations

    experiences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     miracle
    -0.06
     tainted
    -0.06
    /share
    -0.06
     architects
    -0.06
     usuário
    -0.06
     mysl
    -0.06
    .reward
    -0.06
    FORMATION
    -0.06
     melhor
    -0.06
     Painting
    -0.06
    POSITIVE LOGITS
    окол
    0.08
    上的
    0.07
     parody
    0.07
    امج
    0.07
    _CONTAINER
    0.06
     comparison
    0.06
    Map
    0.06
    WORD
    0.06
     progression
    0.06
    encrypt
    0.06
    Act Density 0.065%

    No Known Activations