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

    Neuronpedia

    INDEX
    Explanations

    start of sentence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inward
    -0.08
     czas
    -0.08
     parted
    -0.07
    เป็น
    -0.07
     darr
    -0.07
    -0.07
     reverted
    -0.07
     irresistible
    -0.07
     utterly
    -0.07
    -0.07
    POSITIVE LOGITS
     demonstrates
    0.08
    ák
    0.08
    านคร
    0.08
    鉴
    0.08
     FACT
    0.08
    �
    0.07
     плане
    0.07
    бек
    0.07
     frontières
    0.07
     Steen
    0.07
    Act Density 0.642%
    No Known Activations