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

    Neuronpedia

    INDEX
    Explanations

    code and configuration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	match
    -0.07
    ть
    -0.07
     domin
    -0.07
     fName
    -0.06
     Christianity
    -0.06
     Čech
    -0.06
     же
    -0.06
     Appe
    -0.06
    woo
    -0.06
    ̆
    -0.06
    POSITIVE LOGITS
    Your
    0.07
     Football
    0.06
     started
    0.06
     CREATED
    0.06
     believing
    0.06
     Your
    0.06
    Rec
    0.06
     achieving
    0.06
     REVIEW
    0.06
     synerg
    0.06
    Act Density 0.009%

    No Known Activations