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

    Neuronpedia

    INDEX
    Explanations

    semicolons and parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Stevens
    -0.07
    (~
    -0.07
     ignorance
    -0.07
    idae
    -0.06
     getaway
    -0.06
    仕
    -0.06
     Beijing
    -0.06
    _RST
    -0.06
     observer
    -0.06
    CEPTION
    -0.06
    POSITIVE LOGITS
    ieux
    0.07
    elerine
    0.07
    .ai
    0.06
     flip
    0.06
    NYSE
    0.06
    Turn
    0.06
    uest
    0.06
    ahun
    0.06
     nữa
    0.06
    ulfilled
    0.06
    Act Density 0.013%

    No Known Activations