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

    Neuronpedia

    INDEX
    Explanations

    math and diagrams

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pomi
    -0.07
    樟
    -0.07
     erotico
    -0.07
    YouTube
    -0.07
     waving
    -0.07
     giản
    -0.07
     Çok
    -0.07
     sık
    -0.06
     pathetic
    -0.06
    apo
    -0.06
    POSITIVE LOGITS
    _coverage
    0.07
    标
    0.07
     CE
    0.07
    IBE
    0.07
    幣
    0.07
     Hunger
    0.07
    _adj
    0.07
    bright
    0.07
    (sub
    0.07
     owners
    0.06
    Act Density 0.042%

    No Known Activations