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

    Neuronpedia

    INDEX
    Explanations

    social media handles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sicherheit
    0.61
     Privacidade
    0.59
     Physicians
    0.58
     Poor
    0.56
     Safety
    0.56
     Trusted
    0.55
    的安全
    0.55
     Pediatric
    0.54
     безопас
    0.51
     Standards
    0.51
    POSITIVE LOGITS
     когда
    0.62
     município
    0.57
    elemento
    0.57
     textura
    0.57
    necklace
    0.56
     потім
    0.55
    ''(
    0.55
     göz
    0.55
     necklace
    0.55
    trombone
    0.54
    Act Density 0.000%

    No Known Activations