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

    Neuronpedia

    INDEX
    Explanations

    work

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     하지만
    -0.07
    Delay
    -0.07
    gulp
    -0.07
     земля
    -0.07
     delays
    -0.06
    (height
    -0.06
     consuming
    -0.06
    _numero
    -0.06
    less
    -0.06
    ishing
    -0.06
    POSITIVE LOGITS
    �
    0.06
    urable
    0.06
     �
    0.06
    ervo
    0.06
     conclusive
    0.06
     Franken
    0.06
    ーター
    0.06
    ｒ
    0.06
    ﺮ
    0.06
     hợp
    0.06
    Act Density 0.023%

    No Known Activations