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

    Neuronpedia

    INDEX
    Explanations

    basics, functions, algebra

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pagar
    0.54
     exigir
    0.51
     bathrobe
    0.48
     membayar
    0.48
    bedrooms
    0.48
    φε
    0.47
     atractivo
    0.47
     aprobación
    0.46
     favoriser
    0.46
    lebihan
    0.45
    POSITIVE LOGITS
     basics
    0.88
     Basics
    0.86
     Fundamentals
    0.81
     Algebra
    0.77
     fundamentals
    0.76
    Fundamentals
    0.70
     Principles
    0.68
     அடிப்பட
    0.66
    Algebra
    0.66
     basic
    0.65
    Act Density 0.187%

    No Known Activations