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

    Neuronpedia

    INDEX
    Explanations

    @@

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "For
    -0.07
     behaved
    -0.07
     div
    -0.06
    “For
    -0.06
     ح
    -0.06
    -mile
    -0.06
    "After
    -0.06
     Admir
    -0.06
    ,'\
    -0.06
     defendants
    -0.06
    POSITIVE LOGITS
    Authority
    0.07
     jit
    0.06
    0.06
    .Graphics
    0.06
     Gong
    0.06
     Gott
    0.06
     floppy
    0.06
    _proba
    0.06
     derecho
    0.06
     arts
    0.06
    Act Density 0.001%

    No Known Activations