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

    Neuronpedia

    INDEX
    Explanations

    accounting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Indices
    -0.08
    Cities
    -0.08
     Janeiro
    -0.08
    Steps
    -0.08
     hafa
    -0.08
    Commands
    -0.07
    аста
    -0.07
     Vocal
    -0.07
    орист
    -0.07
    Voice
    -0.07
    POSITIVE LOGITS
     inflated
    0.10
     preserved
    0.09
    称
    0.08
     reconstructed
    0.08
     duplicated
    0.08
    ราค
    0.08
     purchaser
    0.08
     survivor
    0.08
     yol
    0.08
    稱
    0.08
    Act Density 0.005%

    No Known Activations