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

    Neuronpedia

    INDEX
    Explanations

    prepositions in formal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    osg
    -0.26
    wizard
    -0.26
    iy
    -0.25
     shaving
    -0.25
    ultan
    -0.24
    oppel
    -0.24
    éļ¼
    -0.24
     later
    -0.24
     Lone
    -0.24
    oit
    -0.23
    POSITIVE LOGITS
    çļĦæĬķèµĦ
    0.28
     Tang
    0.25
     xu
    0.25
    keys
    0.25
     paraph
    0.25
    æĬķèµĦé¢Ŀ
    0.24
    ure
    0.24
    缪
    0.24
    äºĶ个
    0.24
    Mob
    0.24
    Act Density 6.603%

    No Known Activations