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

    Neuronpedia

    INDEX
    Explanations

    words followed by to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    க்காக
    0.61
     עבור
    0.60
    வதற்காக
    0.51
    ക്കായി
    0.50
     కోసం
    0.48
    ത്തിനായി
    0.45
     үчүн
    0.45
    ளுக்காக
    0.42
    为止
    0.42
     أجل
    0.41
    POSITIVE LOGITS
     kepada
    2.28
     to
    1.89
     إلى
    1.77
    到
    1.73
     към
    1.50
     thereto
    1.42
     الى
    1.40
    ដល់
    1.40
    to
    1.37
     aos
    1.34
    Act Density 0.817%

    No Known Activations