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

    Neuronpedia

    INDEX
    Explanations

    ap

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     millennium
    -0.07
    Calculator
    -0.07
     Ca
    -0.07
     reputation
    -0.07
    杏
    -0.07
    鸯
    -0.07
    IJ
    -0.07
     hypertension
    -0.06
    .access
    -0.06
     LS
    -0.06
    POSITIVE LOGITS
    	op
    0.07
    nell
    0.07
    ресурс
    0.07
    Cool
    0.07
     manufact
    0.06
    מוק
    0.06
    谢邀
    0.06
    作者所有
    0.06
     prefab
    0.06
    مول
    0.06
    Act Density 0.002%

    No Known Activations