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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    irc
    -0.07
    _Read
    -0.06
    IRC
    -0.06
     lệnh
    -0.06
    .Expression
    -0.06
     expans
    -0.06
    expand
    -0.06
    čer
    -0.06
    -token
    -0.06
     forgot
    -0.06
    POSITIVE LOGITS
     ContentView
    0.06
     funk
    0.06
    嗎
    0.06
    "]
↵
    0.06
     Luxembourg
    0.06
    prestashop
    0.06
    든
    0.06
    щих
    0.06
     '=',
    0.06
     عش
    0.06
    Act Density 0.001%

    No Known Activations