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

    Neuronpedia

    INDEX
    Explanations

    dest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    换来
    -0.07
    炷
    -0.07
     problems
    -0.06
     fren
    -0.06
    煃
    -0.06
    ➿
    -0.06
     początku
    -0.06
    氤
    -0.06
    荛
    -0.06
    /topic
    -0.06
    POSITIVE LOGITS
    分校
    0.08
     ↑
    0.07
     extinct
    0.07
    braska
    0.07
     External
    0.07
    립
    0.07
    промышлен
    0.07
     confess
    0.07
    Companies
    0.07
    GF
    0.07
    Act Density 0.004%

    No Known Activations