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

    Neuronpedia

    INDEX
    Explanations

    prepositions followed by verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     domino
    0.48
    anchi
    0.47
     Yatha
    0.47
     goto
    0.46
    torch
    0.45
     Zaragoza
    0.45
     id
    0.43
     Yeni
    0.42
     Venezuela
    0.42
     Gama
    0.42
    POSITIVE LOGITS
    නී
    0.55
    зже
    0.52
    เอียด
    0.50
    ラベル
    0.50
    یک
    0.48
    ل
    0.48
    درا
    0.48
    ي
    0.48
    د
    0.47
    Accounting
    0.47
    Act Density 0.001%

    No Known Activations