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

    Neuronpedia

    INDEX
    Explanations

    population demographic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     finder
    -0.08
     Finder
    -0.08
     qualify
    -0.07
     rechter
    -0.07
     Ske
    -0.07
    st
    -0.07
     secure
    -0.07
     Bum
    -0.07
     laminate
    -0.07
    ++
    -0.07
    POSITIVE LOGITS
     bott
    0.10
     viagens
    0.10
    假
    0.09
     matern
    0.09
    ที่ผ่านมา
    0.09
     لوی
    0.09
     historias
    0.09
     lockdown
    0.09
     founding
    0.09
     aventuras
    0.09
    Act Density 0.004%

    No Known Activations