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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     indeed
    -0.08
    <|reserved_200016|>
    -0.08
     כולל
    -0.08
     ethical
    -0.08
    hopefully
    -0.07
    background
    -0.07
     fantasy
    -0.07
     ethically
    -0.07
     تس
    -0.07
    ethical
    -0.07
    POSITIVE LOGITS
     Tong
    0.08
    гө
    0.08
     dimanche
    0.07
     Sup
    0.07
     wawe
    0.07
     Binding
    0.07
     гэтага
    0.07
    pegawai
    0.07
     Noor
    0.07
    _DAY
    0.07
    Act Density 0.306%

    No Known Activations