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

    Neuronpedia

    INDEX
    Explanations

    letters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _experience
    -0.08
     Technology
    -0.08
    CHILD
    -0.07
     alleges
    -0.07
    URT
    -0.07
    webElementProperties
    -0.07
    choices
    -0.07
    嘴里
    -0.06
    ’am
    -0.06
    ument
    -0.06
    POSITIVE LOGITS
     Moh
    0.07
    _ab
    0.07
    叫我
    0.07
     eb
    0.07
    较量
    0.07
     Oslo
    0.07
    沆
    0.07
     mobil
    0.06
    ELCOME
    0.06
    :NO
    0.06
    Act Density 0.043%

    No Known Activations