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

    Neuronpedia

    INDEX
    Explanations

    configuration and creation of software components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Anthrop
    0.44
    Shir
    0.44
    Dried
    0.44
    野球
    0.43
     положении
    0.42
    біль
    0.42
    ні
    0.41
    Из
    0.41
    Turner
    0.41
     Steinmann
    0.41
    POSITIVE LOGITS
     create
    0.55
     util
    0.53
     config
    0.51
     defineConfig
    0.49
     creat
    0.49
     utils
    0.48
     tạo
    0.48
     promis
    0.48
    initializeApp
    0.47
     defaults
    0.47
    Act Density 0.013%

    No Known Activations