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

    Neuronpedia

    INDEX
    Explanations

    New

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    📕
    -0.08
     Riot
    -0.07
    ▧
    -0.07
    itr
    -0.07
    �
    -0.07
    ﮋ
    -0.07
    〃
    -0.06
    ้อง
    -0.06
    大佬
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     shorten
    0.09
     corpor
    0.08
    Matchers
    0.08
    地说
    0.07
     trackers
    0.07
    ��
    0.07
     чувство
    0.07
    urv
    0.07
    从来没有
    0.07
    几个月
    0.07
    Act Density 0.011%

    No Known Activations