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

    Neuronpedia

    INDEX
    Explanations

    Technology-related texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Username
    -0.08
    っています
    -0.07
    います
    -0.07
    秋季
    -0.07
     сайта
    -0.07
    ),
↵
    -0.06
    -U
    -0.06
    .endTime
    -0.06
    消息
    -0.06
    产生
    -0.06
    POSITIVE LOGITS
    とはい
    0.08
    _equiv
    0.07
     металл
    0.07
     (...
    0.07
     nostalg
    0.07
     ancor
    0.06
     Levi
    0.06
    (CC
    0.06
    铫
    0.06
    荭
    0.06
    Act Density 0.163%

    No Known Activations