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

    Neuronpedia

    INDEX
    Explanations

    determiners followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tricky
    0.90
     confus
    0.82
    ρεία
    0.80
     confused
    0.79
     Convenient
    0.78
     relevante
    0.77
     interessant
    0.77
     convenient
    0.76
     smelly
    0.75
     confusing
    0.75
    POSITIVE LOGITS
     words
    0.78
    每一
    0.71
    its
    0.69
     imparted
    0.68
    每一个
    0.68
     workmanship
    0.67
     remarks
    0.66
    一个人
    0.66
     argumentos
    0.65
    رد
    0.65
    Act Density 0.398%

    No Known Activations