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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pancakes
    -0.07
     groceries
    -0.07
     instruction
    -0.07
     slun
    -0.07
     steam
    -0.07
     translation
    -0.06
    σιεύ
    -0.06
     telemetry
    -0.06
    。我
    -0.06
     ware
    -0.06
    POSITIVE LOGITS
     validations
    0.07
    rick
    0.07
    ennes
    0.06
    zenia
    0.06
    eshire
    0.06
     edilir
    0.06
    /max
    0.06
     Lisa
    0.06
    九
    0.06
     things
    0.06
    Act Density 0.013%

    No Known Activations