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

    Neuronpedia

    INDEX
    Explanations

    following conjunctions or prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ជាមួយ
    0.87
    ش
    0.86
     jederzeit
    0.80
    الغ
    0.79
    ون
    0.78
     متنوع
    0.78
    tagName
    0.75
    របស់អ្នក
    0.74
    ق
    0.74
    மி
    0.73
    POSITIVE LOGITS
    s
    1.03
     strangled
    0.79
     그러나
    0.77
    ton
    0.76
    RO
    0.76
     máu
    0.73
    ters
    0.72
    t
    0.71
    0.69
     lifeless
    0.69
    Act Density 0.000%

    No Known Activations