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

    Neuronpedia

    INDEX
    Explanations

    programming variables and numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     planet
    -0.07
     Planet
    -0.07
    _predictions
    -0.06
     Game
    -0.06
    Monster
    -0.06
     pattern
    -0.06
    _PROPERTY
    -0.06
     ER
    -0.06
    ilm
    -0.06
     conflict
    -0.06
    POSITIVE LOGITS
    
    0.06
     สามารถ
    0.06
    เลย
    0.06
     بص
    0.06
    乃
    0.06
     аль
    0.06
    /navbar
    0.06
    ามารถ
    0.06
     прим
    0.06
    ξη
    0.06
    Act Density 0.067%

    No Known Activations