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

    Neuronpedia

    INDEX
    Explanations

    News articles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ㄷ
    -0.08
    airport
    -0.07
    -employed
    -0.07
     mexico
    -0.07
    憑
    -0.07
     llvm
    -0.07
    須
    -0.07
     NM
    -0.07
    赁
    -0.07
     ideally
    -0.07
    POSITIVE LOGITS
    上世纪
    0.07
    ;}
    0.07
    フェ
    0.07
     sought
    0.07
     single
    0.06
     });
↵
    0.06
     kvinne
    0.06
    .some
    0.06
    _SR
    0.06
     Bans
    0.06
    Act Density 0.031%

    No Known Activations