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

    Neuronpedia

    INDEX
    Explanations

    capital city or LV

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     shenanigans
    0.48
    GUI
    0.47
    ';"+
    0.46
    澹
    0.46
    ḗ
    0.46
    썽
    0.46
    하거나
    0.45
    راف
    0.44
     말씀을
    0.43
    œurs
    0.43
    POSITIVE LOGITS
     grassland
    0.52
     Lambda
    0.49
     Services
    0.49
     Brings
    0.49
     describir
    0.47
     Data
    0.47
     Objectives
    0.46
     LONDON
    0.46
     lush
    0.46
     z
    0.46
    Act Density 0.010%

    No Known Activations