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

    Neuronpedia

    INDEX
    Explanations

    installing software packages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     coronavirus
    0.44
     employability
    0.41
     agora
    0.40
    ред
    0.39
     Foo
    0.39
     fruits
    0.39
     soja
    0.39
     componentWill
    0.39
     casks
    0.38
     fars
    0.38
    POSITIVE LOGITS
    ChatGPT
    0.49
    インストール
    0.46
     Installing
    0.46
    Tail
    0.45
     Installations
    0.45
    🩶
    0.45
    tailwindcss
    0.43
     instalación
    0.43
    tailwind
    0.43
    尾
    0.43
    Act Density 0.003%

    No Known Activations