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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (course
    -0.06
    _behavior
    -0.06
    =b
    -0.06
     loader
    -0.06
     singles
    -0.06
     flu
    -0.06
    	props
    -0.06
     grande
    -0.06
     vivid
    -0.06
    leen
    -0.06
    POSITIVE LOGITS
    ixmap
    0.07
     dům
    0.07
     dunk
    0.06
    ecture
    0.06
    PLICATION
    0.06
    roj
    0.06
     سخ
    0.06
    _BITMAP
    0.06
     dj
    0.06
     Hamburg
    0.06
    Act Density 0.143%

    No Known Activations