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

    Neuronpedia

    INDEX
    Explanations

    r

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oment
    -0.07
    onen
    -0.06
    違
    -0.06
    detector
    -0.06
     manžel
    -0.06
    init
    -0.06
    ฐาน
    -0.06
     Positive
    -0.06
    ,get
    -0.06
    	glog
    -0.06
    POSITIVE LOGITS
     disadvantage
    0.07
    -auth
    0.06
    Brazil
    0.06
    快
    0.06
    険
    0.06
     要
    0.06
     PTR
    0.06
    .Fields
    0.06
     dříve
    0.06
    Stretch
    0.05
    Act Density 0.000%

    No Known Activations