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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    otor
    -0.07
    .movie
    -0.07
    ("-");↵
    -0.07
    日报社
    -0.07
     Nuevo
    -0.07
    cobra
    -0.06
    얔
    -0.06
    :D
    -0.06
    continent
    -0.06
     bitterly
    -0.06
    POSITIVE LOGITS
    ⇙
    0.08
    fest
    0.07
     Skill
    0.07
    =[],
    0.07
     سبحان
    0.07
     Spirit
    0.07
    Quote
    0.06
    老
    0.06
    Craft
    0.06
     hvad
    0.06
    Act Density 0.042%

    No Known Activations