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

    Neuronpedia

    INDEX
    Explanations

    prepositions/conjunctions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     //↵
    -0.07
    舌
    -0.06
    ancell
    -0.06
    '):
↵
    -0.06
    _meter
    -0.06
    vio
    -0.06
     aup
    -0.06
    edi
    -0.06
    ندگان
    -0.06
     fuss
    -0.05
    POSITIVE LOGITS
     comics
    0.07
    	ORDER
    0.07
     compute
    0.07
    porno
    0.07
     GRAT
    0.07
     ++)
    0.06
     computes
    0.06
     LIABILITY
    0.06
     商品
    0.06
     Strikes
    0.06
    Act Density 0.042%

    No Known Activations