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

    Neuronpedia

    INDEX
    Explanations

    explaining meaning or definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     personnaliser
    0.58
     configurable
    0.50
     funcionalidad
    0.50
     utilizzare
    0.50
     fonctionnalités
    0.50
     mengakses
    0.50
     dinâmica
    0.49
     kompat
    0.48
     পরিষে
    0.48
     கட்டமை
    0.47
    POSITIVE LOGITS
     lacking
    0.58
     trifling
    0.53
     roused
    0.51
     strikingly
    0.50
     pretended
    0.48
     habitually
    0.48
     lacked
    0.47
     lack
    0.47
     lacks
    0.46
     shrewd
    0.46
    Act Density 0.109%

    No Known Activations