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

    Neuronpedia

    INDEX
    Explanations

    Abstract items

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tów
    -0.07
     tę
    -0.06
     Hunger
    -0.06
     AUX
    -0.06
    ==>
    -0.06
    רן
    -0.06
     votes
    -0.06
    _PLL
    -0.06
    INC
    -0.06
    ᆢ
    -0.06
    POSITIVE LOGITS
     차
    0.08
     comedian
    0.08
    等待
    0.08
     modern
    0.07
     magazines
    0.07
     cleaning
    0.07
    Simple
    0.07
    络
    0.07
    _initializer
    0.07
     mạng
    0.07
    Act Density 0.002%

    No Known Activations