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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     зб
    -0.07
     Martial
    -0.06
     Boss
    -0.06
     Garrison
    -0.06
    Hallo
    -0.06
    ιά
    -0.06
     Burr
    -0.06
    Lou
    -0.06
    _sq
    -0.06
    .FileWriter
    -0.06
    POSITIVE LOGITS
     समझ
    0.07
     Notify
    0.07
    	box
    0.06
     syntax
    0.06
     idle
    0.06
     ranging
    0.06
    ):(
    0.06
     wen
    0.06
    ้ย
    0.06
     треб
    0.06
    Act Density 0.050%

    No Known Activations