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

    Neuronpedia

    INDEX
    Explanations

    verbs related to change followed by direction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    க்காக
    0.43
     വേണ്ടി
    0.39
     עבור
    0.38
     köl
    0.35
    kében
    0.35
     شرطونه
    0.34
     खिलाफ
    0.33
    으로서
    0.33
     앞에서
    0.32
    ຂອງ
    0.32
    POSITIVE LOGITS
     إلى
    1.53
     into
    1.47
    到
    1.46
     الى
    1.27
    到一个
    1.21
     naar
    1.19
    into
    1.16
     ወደ
    1.13
     onto
    1.13
     to
    1.08
    Act Density 0.061%

    No Known Activations