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
    _final
    -0.07
    -shop
    -0.06
     Milo
    -0.06
    _slider
    -0.06
    ेहतर
    -0.06
    -shopping
    -0.06
    	update
    -0.06
    尾
    -0.06
     flawless
    -0.06
    -sw
    -0.06
    POSITIVE LOGITS
    :'',
    0.07
    ının
    0.07
    witter
    0.07
     sacred
    0.07
     sám
    0.06
     Verse
    0.06
    ♀♀♀♀
    0.06
     Ủy
    0.06
     grin
    0.06
     anx
    0.06
    Act Density 0.010%

    No Known Activations