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

    Neuronpedia

    INDEX
    Explanations

    Quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gives
    -0.07
    Pří
    -0.07
     giving
    -0.07
    controllers
    -0.07
     Misc
    -0.07
     stamp
    -0.07
    Misc
    -0.06
     PHY
    -0.06
    Iteration
    -0.06
     Palestine
    -0.06
    POSITIVE LOGITS
    target
    0.07
    尘
    0.06
    则
    0.06
    (response
    0.06
    沒有
    0.06
    .Gen
    0.06
     *&
    0.06
     LP
    0.06
    ，↵↵
    0.06
    itters
    0.06
    Act Density 0.014%

    No Known Activations