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

    Neuronpedia

    INDEX
    Explanations

    Pokemon cards

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     
↵
↵
    -0.09
    今
    -0.08
     arcu
    -0.08
     classics
    -0.08
     classiques
    -0.08
     klasik
    -0.08
    ↵    
↵
    -0.08
    ↵
↵
    -0.07
        
↵
↵
    -0.07
    _RESET
    -0.07
    POSITIVE LOGITS
    hostname
    0.08
     sibling
    0.08
    hela
    0.08
     bail
    0.07
    .hostname
    0.07
     난
    0.07
     hostname
    0.07
     thiện
    0.07
    frontend
    0.07
     breached
    0.07
    Act Density 0.001%

    No Known Activations