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

    Neuronpedia

    INDEX
    Explanations

    code configurations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Forecast
    -0.07
    uga
    -0.06
     condemnation
    -0.06
    _tracker
    -0.06
     compl
    -0.06
     recur
    -0.06
    ction
    -0.06
    .attr
    -0.06
     autom
    -0.06
     countert
    -0.06
    POSITIVE LOGITS
     SIM
    0.07
     Res
    0.07
     TU
    0.07
     -↵↵
    0.06
    Gu
    0.06
    ↵↵
    0.06
     RES
    0.06
    Industrial
    0.06
     screenHeight
    0.06
    Philip
    0.06
    Act Density 0.006%

    No Known Activations