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

    Neuronpedia

    INDEX
    Explanations

    life interesting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sentiments
    0.89
    寞
    0.86
     QM
    0.85
     cat
    0.85
     Cat
    0.84
    Cat
    0.82
     EDP
    0.82
    の
    0.80
     Cathy
    0.80
     palazzo
    0.80
    POSITIVE LOGITS
     필요한
    0.83
     oder
    0.81
     roug
    0.79
     uitle
    0.77
     حداقل
    0.77
     potřeb
    0.76
     eint
    0.76
    యాన్ని
    0.76
     atau
    0.75
     eens
    0.75
    Act Density 0.000%

    No Known Activations