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

    Neuronpedia

    INDEX
    Explanations

    job applications descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dealings
    -0.09
     സംവിധ
    -0.08
     گیر
    -0.08
     ලබා
    -0.08
     ವ್ಯವಸ್ಥ
    -0.08
    -0.08
     unattended
    -0.08
     시스템
    -0.08
     rodit
    -0.07
     MMO
    -0.07
    POSITIVE LOGITS
     aspiring
    0.11
    _candidate
    0.10
     aspire
    0.09
     кандидат
    0.08
     talented
    0.08
     быв
    0.08
     athletic
    0.08
     candidature
    0.08
    加入
    0.08
     destined
    0.08
    Act Density 0.144%
    No Known Activations