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

    Neuronpedia

    INDEX
    Explanations

    generated

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Den
    -0.08
     Young
    -0.08
     Cooling
    -0.08
    _INTERRUP
    -0.08
     INF
    -0.08
     Infinity
    -0.08
     Dement
    -0.08
     sech
    -0.08
     szüks
    -0.08
     elétrica
    -0.08
    POSITIVE LOGITS
     testimonials
    0.11
     отзывы
    0.10
    晒单
    0.10
    投稿
    0.10
    Testimonials
    0.09
    素材
    0.09
     sourced
    0.09
     encouraged
    0.09
     DIY
    0.09
     grassroots
    0.08
    Act Density 0.015%

    No Known Activations