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

    Neuronpedia

    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ♪
    -0.07
    国土资源
    -0.07
    sass
    -0.07
    还想
    -0.07
    岁月
    -0.07
     PLC
    -0.07
    積極
    -0.07
    源源不断
    -0.06
    artifact
    -0.06
    趑
    -0.06
    POSITIVE LOGITS
    מעשה
    0.07
    Han
    0.07
    ."↵↵
    0.07
     Deletes
    0.07
    	alpha
    0.07
    古代
    0.06
    dispatch
    0.06
     bc
    0.06
     married
    0.06
    _Statics
    0.06
    Act Density 0.035%

    No Known Activations