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

    Neuronpedia

    INDEX
    Explanations

    math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Costume
    -0.07
    Relative
    -0.07
    ificantly
    -0.06
     NF
    -0.06
     smokers
    -0.06
    Tim
    -0.06
     Cor
    -0.06
     Born
    -0.06
    Peer
    -0.06
    лим
    -0.06
    POSITIVE LOGITS
     dẫn
    0.07
    撤
    0.06
    сутств
    0.06
     Dự
    0.06
     исключ
    0.06
     혹
    0.06
    σουν
    0.06
     )↵
    0.06
     teslim
    0.06
     покры
    0.06
    Act Density 0.016%

    No Known Activations