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
    的孩子
    -0.07
     temps
    -0.07
     реклам
    -0.07
    _cache
    -0.06
    odom
    -0.06
    民办
    -0.06
    צע
    -0.06
     mentor
    -0.06
    现场
    -0.06
     Smoke
    -0.06
    POSITIVE LOGITS
    bfd
    0.07
    .arrow
    0.07
    妨碍
    0.07
    保温
    0.07
     세계
    0.07
    fd
    0.07
     expecting
    0.06
    ề
    0.06
    .owl
    0.06
    sv
    0.06
    Act Density 0.331%

    No Known Activations