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

    Neuronpedia

    INDEX
    Explanations

    varied text excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     functools
    -0.07
     Yet
    -0.06
    �
    -0.06
     Budget
    -0.06
     Ipsum
    -0.06
    HomeAsUp
    -0.06
     �
    -0.06
     �
    -0.06
     Insets
    -0.06
     Crime
    -0.06
    POSITIVE LOGITS
    /legal
    0.07
     중국
    0.07
    ":"+
    0.07
    ?a
    0.06
    thy
    0.06
    иком
    0.06
     ignored
    0.06
    ev
    0.06
    (sprite
    0.06
    ستم
    0.06
    Act Density 0.000%

    No Known Activations