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

    Neuronpedia

    INDEX
    Explanations

    format

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cell
    -0.07
     psy
    -0.07
     Ly
    -0.07
     spy
    -0.07
     oxy
    -0.07
     ear
    -0.07
     cells
    -0.07
    706
    -0.06
     eye
    -0.06
     tang
    -0.06
    POSITIVE LOGITS
     format
    0.11
     Format
    0.10
    Format
    0.09
     formats
    0.08
    Formatting
    0.08
    .format
    0.08
    FORMAT
    0.08
    format
    0.08
    /format
    0.08
    _format
    0.08
    Act Density 0.031%

    No Known Activations