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

    Neuronpedia

    INDEX
    Explanations

    Language names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     replicas
    -0.10
     denominations
    -0.09
     replica
    -0.09
     bino
    -0.09
    dos
    -0.07
     stage
    -0.07
    blers
    -0.07
     доз
    -0.07
     replic
    -0.07
     Marbella
    -0.07
    POSITIVE LOGITS
     enigmatic
    0.13
     unidentified
    0.10
     Independent
    0.09
     mysterious
    0.09
    UNKNOWN
    0.09
     Civilization
    0.09
     primordial
    0.09
    Independent
    0.09
    (::
    0.09
     неизвест
    0.09
    Act Density 0.017%

    No Known Activations