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

    Neuronpedia

    INDEX
    Explanations

    instructions and generation prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     arterioles
    0.31
     dici
    0.29
    slf
    0.29
     Atkins
    0.28
     Causes
    0.27
     homologous
    0.27
    bigl
    0.27
    ূ
    0.27
     वा
    0.27
     Serrano
    0.27
    POSITIVE LOGITS
    生成
    0.42
     markdown
    0.36
    Generating
    0.34
    Generate
    0.34
     生成
    0.34
    回复
    0.34
    SQL
    0.33
    GPT
    0.32
     继续
    0.32
    코드
    0.32
    Act Density 0.055%

    No Known Activations