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

    Neuronpedia

    INDEX
    Explanations

    sequels

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    consumer
    -0.07
     fict
    -0.06
    iao
    -0.06
    .ini
    -0.06
     gatherings
    -0.06
    emens
    -0.06
     Inquiry
    -0.06
     제품
    -0.06
    associate
    -0.06
    Playing
    -0.06
    POSITIVE LOGITS
     interesting
    0.07
    τς
    0.07
    --)↵
    0.07
    unuz
    0.07
     всього
    0.07
     vivid
    0.07
    今
    0.06
    sym
    0.06
     有
    0.06
     afflict
    0.06
    Act Density 0.037%

    No Known Activations