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

    Neuronpedia

    INDEX
    Explanations

    colon

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stolen
    -0.08
    Streaming
    -0.08
     arr
    -0.07
    赶来
    -0.07
     Gret
    -0.07
     broke
    -0.07
    屿
    -0.07
    "They
    -0.07
    Hong
    -0.07
     beds
    -0.07
    POSITIVE LOGITS
     colon
    0.08
     Pulitzer
    0.07
    PM
    0.07
    ප
    0.07
     towering
    0.07
     интерьер
    0.07
     subt
    0.07
    클
    0.07
    .chars
    0.07
    سطح
    0.06
    Act Density 0.007%

    No Known Activations