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

    Neuronpedia

    INDEX
    Explanations

    Docker layers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stund
    -0.08
     pescado
    -0.08
     tending
    -0.08
     visiting
    -0.08
     ade
    -0.08
     government
    -0.07
     loc
    -0.07
     cc
    -0.07
     cast
    -0.07
     concession
    -0.07
    POSITIVE LOGITS
     Layers
    0.10
     immutable
    0.09
    _steps
    0.09
    layers
    0.09
    steps
    0.09
     Schritte
    0.09
    .layers
    0.09
    [layer
    0.08
     stappen
    0.08
    immutable
    0.08
    Act Density 0.002%

    No Known Activations