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

    Neuronpedia

    INDEX
    Explanations

    code generation tools

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     theories
    0.37
     decoded
    0.37
     lắp
    0.36
     lounges
    0.35
    reys
    0.35
     amassed
    0.34
     божомолу
    0.34
    unoassay
    0.34
    endas
    0.33
     colorless
    0.33
    POSITIVE LOGITS
     generator
    0.79
     tool
    0.77
     Generate
    0.76
    工具
    0.75
    Generate
    0.73
     Generator
    0.73
    生成
    0.73
     generators
    0.71
    generate
    0.69
    Generator
    0.69
    Act Density 0.007%

    No Known Activations