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

    Neuronpedia

    INDEX
    Explanations

    Units of measure

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    init
    -0.07
    along
    -0.07
     ~(
    -0.07
    تامبر
    -0.07
    东
    -0.06
    ترین
    -0.06
     United
    -0.06
    těl
    -0.06
     false
    -0.06
    amient
    -0.06
    POSITIVE LOGITS
     TSR
    0.07
     fullPath
    0.07
    SCALE
    0.07
     度
    0.06
    !=↵
    0.06
     limb
    0.06
     قص
    0.06
     hrs
    0.06
     глу
    0.06
    (WebDriver
    0.06
    Act Density 0.113%

    No Known Activations