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

    Neuronpedia

    INDEX
    Explanations

    intended

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    薪
    -0.08
    来源于
    -0.08
    �
    -0.07
     Operational
    -0.07
     phen
    -0.07
    胚
    -0.07
     Gross
    -0.07
    脓
    -0.06
    逐年
    -0.06
     Abraham
    -0.06
    POSITIVE LOGITS
    --[
    0.07
     lj
    0.07
     scenes
    0.07
    toList
    0.07
     lim
    0.07
    'une
    0.07
     system
    0.06
    异味
    0.06
     Lý
    0.06
     winger
    0.06
    Act Density 0.000%

    No Known Activations