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

    Neuronpedia

    INDEX
    Explanations

    Code/Programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Founded
    -0.07
    Constraint
    -0.06
     Sunder
    -0.06
     Sharia
    -0.06
     Dou
    -0.06
     Ledger
    -0.06
     AFC
    -0.06
    domain
    -0.06
     vomiting
    -0.06
     take
    -0.06
    POSITIVE LOGITS
     слив
    0.07
     mysqli
    0.07
    ”:
    0.06
     %-
    0.06
    ."</
    0.06
     thăm
    0.06
    ือ
    0.06
     Ku
    0.06
     "}↵
    0.06
     arguments
    0.06
    Act Density 0.003%

    No Known Activations