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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    serialization
    -0.07
     Metric
    -0.07
    /tmp
    -0.06
    PathParam
    -0.06
    Blo
    -0.06
    editar
    -0.06
    /english
    -0.06
    .Zip
    -0.06
     ));
↵
    -0.06
    Chess
    -0.06
    POSITIVE LOGITS
    便
    0.07
     signify
    0.07
     registering
    0.07
    *w
    0.06
    注意
    0.06
     bak
    0.06
     intrigued
    0.06
    secret
    0.06
    ONGO
    0.06
     PLEASE
    0.06
    Act Density 0.001%

    No Known Activations