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

    Neuronpedia

    INDEX
    Explanations

    Hamming codes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     persuasion
    -0.09
     Push
    -0.08
     Polly
    -0.08
     Florian
    -0.08
     persuade
    -0.07
     cocos
    -0.07
     opt
    -0.07
     bataille
    -0.07
     aquatic
    -0.07
     Wettbewer
    -0.07
    POSITIVE LOGITS
    Diagnostic
    0.09
     실시
    0.08
    Diagnosis
    0.08
    Authorities
    0.08
     диагност
    0.08
     시행
    0.08
     Syndrome
    0.08
     പരിശോധന
    0.08
     Diagnostic
    0.08
     diagnostic
    0.07
    Act Density 0.002%

    No Known Activations