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

    Neuronpedia

    INDEX
    Explanations

    decision-making

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    RP
    -0.08
    还
    -0.07
     מ
    -0.07
     includes
    -0.07
     הלב
    -0.07
    ahu
    -0.06
    缺少
    -0.06
    我认为
    -0.06
    ائد
    -0.06
    _ep
    -0.06
    POSITIVE LOGITS
    культур
    0.07
    魉
    0.07
    QUERY
    0.07
     consc
    0.06
    潜
    0.06
     şek
    0.06
    굿
    0.06
    琀
    0.06
    下來
    0.06
    CLIENT
    0.06
    Act Density 0.091%

    No Known Activations