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

    Neuronpedia

    INDEX
    Explanations

    prepositions followed by verbs or nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     this
    0.46
     ఈ
    0.41
    自己的
    0.37
     этому
    0.37
    ఈ
    0.37
    这个
    0.36
     ресто
    0.36
     monoxide
    0.36
     алкого
    0.36
     mů
    0.35
    POSITIVE LOGITS
    čkom
    0.45
    from
    0.45
    et
    0.45
    ff
    0.45
    line
    0.44
    arm
    0.43
    ഡ്
    0.43
    Whoever
    0.42
    ill
    0.42
    *,
    0.41
    Act Density 1.015%

    No Known Activations