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

    Neuronpedia

    INDEX
    Explanations

    development

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    6
    0.57
    3
    0.51
    1
    0.50
    8
    0.48
    4
    0.48
    7
    0.48
    .
    0.48
    </h3>
    0.46
    은
    0.44
    </h2>
    0.43
    POSITIVE LOGITS
     desarroll
    0.57
     Develop
    0.57
    develop
    0.55
     dezvolt
    0.54
     razvoj
    0.54
     desarrollo
    0.54
    Develop
    0.52
     develop
    0.50
     entwick
    0.50
     développ
    0.50
    Act Density 0.027%

    No Known Activations