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

    Neuronpedia

    INDEX
    Explanations

    Discourse markers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rolled
    -0.07
    Claims
    -0.07
    atts
    -0.07
     Adapt
    -0.07
     endless
    -0.07
     GROUP
    -0.06
     Charge
    -0.06
     rents
    -0.06
     Surround
    -0.06
     Pearson
    -0.06
    POSITIVE LOGITS
     socioeconomic
    0.08
     світ
    0.07
    (il
    0.07
    .getClass
    0.07
     ของ
    0.07
     ตร
    0.06
     quot
    0.06
    .textAlignment
    0.06
    _MetaData
    0.06
    σωπ
    0.06
    Act Density 0.040%

    No Known Activations