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

    Neuronpedia

    INDEX
    Explanations

    elines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     essere
    -0.07
     theft
    -0.07
     Adam
    -0.06
     performances
    -0.06
    猪
    -0.06
     roof
    -0.06
    、彼
    -0.06
     attractions
    -0.06
    "Oh
    -0.06
     Sacr
    -0.06
    POSITIVE LOGITS
     guidelines
    0.21
     Guidelines
    0.18
     guideline
    0.13
     Inline
    0.08
    leading
    0.07
    ide
    0.07
     klin
    0.07
     tutorial
    0.07
    Tooltip
    0.07
    \Middleware
    0.07
    Act Density 0.009%

    No Known Activations