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

    Neuronpedia

    INDEX
    Explanations

    hiding

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    入睡
    -0.08
    ﭝ
    -0.07
    社会组织
    -0.07
    üb
    -0.07
    (sequence
    -0.07
    ultur
    -0.07
    登场
    -0.06
     happ
    -0.06
    身创造
    -0.06
     '_
    -0.06
    POSITIVE LOGITS
    -leaning
    0.07
     gravitational
    0.07
    最大化
    0.07
     mistake
    0.07
    сыл
    0.07
    搌
    0.07
     similar
    0.06
    .annotation
    0.06
     FL
    0.06
     condu
    0.06
    Act Density 0.047%

    No Known Activations