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

    Neuronpedia

    INDEX
    Explanations

    race

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DDL
    -0.07
    顯
    -0.06
     Chains
    -0.06
    bdd
    -0.06
    _MISSING
    -0.06
     Repository
    -0.06
    增长
    -0.06
     졸
    -0.06
     nostr
    -0.06
    显
    -0.06
    POSITIVE LOGITS
    enced
    0.07
     DRIVE
    0.06
     ;
↵
↵
    0.06
     όλ
    0.06
    							
↵
    0.06
     ""
↵
    0.06
            
↵        
↵
    0.06
     datingside
    0.06
    normalize
    0.06
     Blonde
    0.06
    Act Density 0.005%

    No Known Activations