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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tiềm
    -0.07
    展现了
    -0.07
    .dis
    -0.06
    -find
    -0.06
     구
    -0.06
     Doub
    -0.06
     SUS
    -0.06
     Bec
    -0.06
    :title
    -0.06
    acist
    -0.06
    POSITIVE LOGITS
     plugins
    0.07
    ]:=
    0.07
    ernetes
    0.07
     Bukkit
    0.07
    ております
    0.06
    しております
    0.06
    optimizer
    0.06
    asing
    0.06
     poorest
    0.06
     quotas
    0.06
    Act Density 0.003%

    No Known Activations