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

    Neuronpedia

    INDEX
    Explanations

    definitely

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .scenes
    -0.07
    718
    -0.06
    Elite
    -0.06
    Calibri
    -0.06
     Hol
    -0.06
     defenders
    -0.06
    Directory
    -0.06
     메
    -0.06
     extingu
    -0.06
     hol
    -0.06
    POSITIVE LOGITS
    іль
    0.07
     кім
    0.07
    pee
    0.06
    oute
    0.06
    stick
    0.06
     darüber
    0.06
     hist
    0.06
     crust
    0.06
    *:
    0.06
     quoting
    0.06
    Act Density 0.067%

    No Known Activations