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

    Neuronpedia

    INDEX
    Explanations

    education

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     experience
    -1.21
    Experience
    -1.19
     Experience
    -1.15
    experience
    -1.13
     EXPERIENCE
    -1.13
     esperienza
    -1.08
     expérience
    -0.95
     experiencia
    -0.93
     Experiences
    -0.90
     experiência
    -0.87
    POSITIVE LOGITS
     top
    0.66
     mar
    0.59
     Net
    0.57
    BindView
    0.56
     the
    0.56
     net
    0.56
    savevideo
    0.56
    ]]]
    0.56
     her
    0.55
     no
    0.54
    Act Density 1.656%

    No Known Activations