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

    Neuronpedia

    INDEX
    Explanations

    error conditions/test outcomes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     appeals
    -0.07
    synthesize
    -0.06
    ラン
    -0.06
    _code
    -0.06
     alanı
    -0.06
     Кол
    -0.06
     widget
    -0.06
    "<?
    -0.06
    าบาล
    -0.06
    DOMAIN
    -0.06
    POSITIVE LOGITS
    vip
    0.07
     azimuth
    0.06
    vál
    0.06
    .instant
    0.06
     twists
    0.06
    itor
    0.06
     resident
    0.06
    िलन
    0.06
    ouchers
    0.06
     територ
    0.06
    Act Density 0.016%

    No Known Activations