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

    Neuronpedia

    INDEX
    Explanations

    Express

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ैट
    -0.07
    戒
    -0.07
    778
    -0.07
    vidia
    -0.07
     shut
    -0.07
    =db
    -0.07
     suicidal
    -0.07
     Carb
    -0.06
    ็ค
    -0.06
     sebep
    -0.06
    POSITIVE LOGITS
     Express
    0.21
    Express
    0.15
     EXPRESS
    0.14
    express
    0.13
     express
    0.13
     expressly
    0.11
     Cypress
    0.10
    (express
    0.09
     Cyrus
    0.08
     expressing
    0.08
    Act Density 0.007%

    No Known Activations