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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     завд
    -0.07
    記事
    -0.06
    XB
    -0.06
     �
    -0.06
    esy
    -0.06
     Kemp
    -0.06
     lékař
    -0.06
    リス
    -0.06
     벽
    -0.06
     objekt
    -0.06
    POSITIVE LOGITS
    ','');↵
    0.07
    parated
    0.07
    .Before
    0.07
    903
    0.07
     Shops
    0.07
     Dame
    0.06
    _DECL
    0.06
     renovated
    0.06
     trận
    0.06
     Proof
    0.06
    Act Density 0.002%

    No Known Activations