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

    Neuronpedia

    INDEX
    Explanations

    Gradio web interfaces

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Succeeded
    -0.09
     Archbishop
    -0.08
    unnik
    -0.08
     consideración
    -0.08
    Leaving
    -0.08
    gående
    -0.08
    ฝ่าย
    -0.08
    席
    -0.08
    Dato
    -0.08
     audiencia
    -0.08
    POSITIVE LOGITS
     интерф
    0.08
     удоб
    0.08
     interface
    0.08
    .py
    0.08
     formulations
    0.08
     형태
    0.08
    .output
    0.08
    .model
    0.08
     formulate
    0.08
     protoc
    0.08
    Act Density 0.007%

    No Known Activations