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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ("**
    -0.06
     Feeling
    -0.06
    InOut
    -0.06
    purple
    -0.06
    ética
    -0.06
     státní
    -0.06
    BYTE
    -0.06
    countries
    -0.06
    工程
    -0.06
     البلد
    -0.06
    POSITIVE LOGITS
     FRA
    0.06
    ParticleSystem
    0.06
     jug
    0.06
     Short
    0.06
     Sussex
    0.06
     Liquid
    0.06
    (pair
    0.06
    ा।
    0.06
       
↵
    0.06
     poměr
    0.06
    Act Density 0.120%

    No Known Activations