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

    Neuronpedia

    INDEX
    Explanations

    prepositions followed by various words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    り
    0.92
     randomNumber
    0.84
     remarked
    0.82
     historian
    0.80
     screenwriter
    0.79
     violinist
    0.79
    ،
    0.79
    พ์
    0.78
     freelance
    0.77
     wasn
    0.77
    POSITIVE LOGITS
    𝐨
    1.02
    ع
    0.98
    𝐚
    0.97
    exhaust
    0.89
    ഋ
    0.88
    们的
    0.85
    or
    0.84
    жи
    0.83
    κο
    0.83
    কেবল
    0.83
    Act Density 0.001%

    No Known Activations