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

    Neuronpedia

    INDEX
    Explanations

    .title

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     служ
    -0.07
    ueur
    -0.07
    (rank
    -0.06
    υμ
    -0.06
    -color
    -0.06
     GRAT
    -0.06
    help
    -0.06
     skutečnosti
    -0.06
    agents
    -0.06
     newsp
    -0.06
    POSITIVE LOGITS
     incapac
    0.06
    Complex
    0.06
     스
    0.06
    .title
    0.06
     střední
    0.06
    _hierarchy
    0.06
     Tub
    0.06
     Cycling
    0.06
    чки
    0.06
    Haunted
    0.06
    Act Density 0.002%

    No Known Activations