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

    Neuronpedia

    INDEX
    Explanations

    retailer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     disturb
    -0.06
    _annotation
    -0.06
     philosophical
    -0.06
     Disclosure
    -0.06
    	auto
    -0.06
     Save
    -0.06
    animation
    -0.06
     Giấy
    -0.06
     общ
    -0.06
    .SpringBootApplication
    -0.06
    POSITIVE LOGITS
     wishing
    0.07
     smugg
    0.07
     indeed
    0.06
    tü
    0.06
     registering
    0.06
    getUser
    0.06
     excelente
    0.06
    oard
    0.06
    .generate
    0.06
     都
    0.06
    Act Density 0.001%

    No Known Activations