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

    Neuronpedia

    INDEX
    Explanations

    designing and processing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     통
    -0.07
    规定的
    -0.07
    מכר
    -0.07
     Ald
    -0.07
     mechanics
    -0.07
     American
    -0.06
    主要包括
    -0.06
     af
    -0.06
     Depending
    -0.06
     wrapped
    -0.06
    POSITIVE LOGITS
    egot
    0.07
    INDEX
    0.07
    فعاليات
    0.07
    .Editor
    0.07
    𝐽
    0.06
     fonts
    0.06
     Initi
    0.06
    냔
    0.06
    ileged
    0.06
    Front
    0.06
    Act Density 0.061%

    No Known Activations