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

    Neuronpedia

    INDEX
    Explanations

    NTP servers

    np_max-act-logits · gemini-2.0-flashTriggered by @majianfei030706
    New Auto-Interp
    Negative Logits
    -white
    -0.07
     shocking
    -0.07
     likeness
    -0.07
     slight
    -0.06
     clearly
    -0.06
    ประธาน
    -0.06
     offensive
    -0.06
    rawler
    -0.06
    _HTTP
    -0.06
    清洁
    -0.06
    POSITIVE LOGITS
    部
    0.07
    ╃
    0.06
     parts
    0.06
     opted
    0.06
    耕
    0.06
    会产生
    0.06
    𫭢
    0.06
    郊
    0.06
     Ment
    0.06
     unintended
    0.06
    Act Density 0.089%

    No Known Activations