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

    Neuronpedia

    INDEX
    Explanations

    graph theory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cheat
    -0.09
    博士
    -0.09
     niches
    -0.08
    Cheque
    -0.08
     Gregorian
    -0.08
    Jdbc
    -0.08
     Zeit
    -0.08
     吉祥
    -0.08
     Umgang
    -0.08
    科学院
    -0.08
    POSITIVE LOGITS
     connectivity
    0.11
     Connectivity
    0.10
     الدفاع
    0.09
     resilience
    0.09
     защиты
    0.09
    Connectivity
    0.09
     redundancy
    0.09
     resil
    0.09
     دفاع
    0.08
     resilient
    0.08
    Act Density 0.005%

    No Known Activations