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

    Neuronpedia

    INDEX
    Explanations

    Names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Worst
    -0.07
     evt
    -0.06
     Morse
    -0.06
    陶
    -0.06
    -testing
    -0.06
    .fun
    -0.06
    annis
    -0.06
    τολ
    -0.06
     debido
    -0.05
     liebe
    -0.05
    POSITIVE LOGITS
    ...");↵
    0.06
     elf
    0.06
     Kit
    0.06
    ")))
    0.06
    Restaurant
    0.06
     Portrait
    0.06
     město
    0.06
    ategorie
    0.06
    `;
    0.06
     Commercial
    0.06
    Act Density 0.110%

    No Known Activations