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

    Neuronpedia

    INDEX
    Explanations

    varied questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    лагч
    -0.08
    COR
    -0.07
     ofrecer
    -0.07
     APIs
    -0.07
     enhancements
    -0.07
     COR
    -0.07
    हरूले
    -0.07
     ofrecen
    -0.07
     maf
    -0.07
     called
    -0.07
    POSITIVE LOGITS
    ↵			↵
    0.09
    strict
    0.08
     nop
    0.08
    	item
    0.07
     MGM
    0.07
     altro
    0.07
    					↵
    0.07
    ថ្មី
    0.07
    	dialog
    0.07
     oat
    0.07
    Act Density 0.325%

    No Known Activations