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

    Neuronpedia

    INDEX
    Explanations

    preposition followed by target

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    改变
    0.45
     расстоя
    0.45
    າມາດ
    0.45
     ferv
    0.44
     devotee
    0.44
    Denne
    0.44
    ık
    0.44
    ꯌ
    0.44
    parvec
    0.43
     ამ
    0.43
    POSITIVE LOGITS
     Jong
    0.44
     Remix
    0.44
     Smartphones
    0.43
     Rockets
    0.43
     Than
    0.42
    一些
    0.41
     Tig
    0.41
     Runnable
    0.41
     Mult
    0.41
    !]
    0.41
    Act Density 0.003%

    No Known Activations