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

    Neuronpedia

    INDEX
    Explanations

    AT

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ashi
    -0.07
     bilgiler
    -0.07
     destroy
    -0.06
    anker
    -0.06
     bomber
    -0.06
    Dat
    -0.06
     Patel
    -0.06
     Destroy
    -0.06
     certificates
    -0.06
     Singh
    -0.06
    POSITIVE LOGITS
     allot
    0.08
    DISABLE
    0.07
     geared
    0.06
        
↵    
↵
    0.06
     Lodge
    0.06
     önüne
    0.06
    及び
    0.06
    jured
    0.06
            
↵        
↵
    0.06
     earthqu
    0.06
    Act Density 0.016%

    No Known Activations