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

    Neuronpedia

    INDEX
    Explanations

    citations and references

    np_max-act-logits · gemini-2.0-flashTriggered by @majianfei030706
    New Auto-Interp
    Negative Logits
    $user
    -0.07
     Physicians
    -0.07
     pièce
    -0.07
    长沙
    -0.07
    ⎒
    -0.07
    	mc
    -0.06
     kenn
    -0.06
     alc
    -0.06
     ноя
    -0.06
     Suarez
    -0.06
    POSITIVE LOGITS
    关于
    0.08
    的基本
    0.07
    .Find
    0.07
     friendly
    0.07
     Regex
    0.07
     "'";↵
    0.07
    打扮
    0.07
     Xin
    0.07
    tti
    0.06
    oting
    0.06
    Act Density 0.083%

    No Known Activations