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

    Neuronpedia

    INDEX
    Explanations

    age

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     initialValues
    -0.07
     conscious
    -0.07
     Erf
    -0.07
     entrada
    -0.07
     long
    -0.07
    Broken
    -0.06
     nl
    -0.06
     円
    -0.06
    ×
    -0.06
    rss
    -0.06
    POSITIVE LOGITS
    AGE
    0.07
     наблюд
    0.07
     ở
    0.07
     Ashton
    0.07
    inha
    0.07
    境
    0.06
     تج
    0.06
     mediante
    0.06
    mploy
    0.06
     تحت
    0.06
    Act Density 0.003%

    No Known Activations