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

    Neuronpedia

    INDEX
    Explanations

    guideline

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     πάρ
    -0.08
     jackpots
    -0.08
    مين
    -0.08
     bisogno
    -0.08
     george
    -0.08
     personaje
    -0.07
     пас
    -0.07
     besoin
    -0.07
    Sac
    -0.07
     narrator
    -0.07
    POSITIVE LOGITS
     guidelines
    0.14
     Guidelines
    0.13
    指南
    0.11
     guideline
    0.10
    规范
    0.10
     outlines
    0.10
     dotyczą
    0.10
     Guidance
    0.10
     guidance
    0.09
    指导
    0.09
    Act Density 0.038%

    No Known Activations