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

    Neuronpedia

    INDEX
    Explanations

    source code/licenses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Spencer
    -0.07
     питания
    -0.07
    opers
    -0.07
     Ludwig
    -0.06
    ipheral
    -0.06
     Ministers
    -0.06
     Embassy
    -0.06
     launder
    -0.06
     управления
    -0.06
     Wa
    -0.06
    POSITIVE LOGITS
     如
    0.07
     tecn
    0.07
     ==============================================================
    0.06
    arb
    0.06
    had
    0.06
     zł
    0.06
    ンディ
    0.06
     lumin
    0.06
    alleries
    0.06
     parentheses
    0.06
    Act Density 0.028%

    No Known Activations