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

    Neuronpedia

    INDEX
    Explanations

    formal or official actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Особенно
    0.87
     느끼
    0.85
     vytvá
    0.82
     idées
    0.78
     microcosm
    0.77
     angene
    0.77
     maî
    0.77
     সুখী
    0.75
     добре
    0.75
    練習
    0.75
    POSITIVE LOGITS
     pursuant
    0.96
     formal
    0.89
     definitive
    0.86
     prelim
    0.82
     mediante
    0.79
     after
    0.79
     tramite
    0.78
     بواسطة
    0.77
     officially
    0.76
     via
    0.75
    Act Density 0.020%

    No Known Activations