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

    Neuronpedia

    INDEX
    Explanations

    prepositions and infinitival markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     precludes
    0.48
     provides
    0.44
     remains
    0.44
     обеспечивает
    0.43
    -
    0.43
     providing
    0.43
     necessitating
    0.42
     Institution
    0.41
     tightened
    0.41
     있으며
    0.41
    POSITIVE LOGITS
    برای
    0.59
     untuk
    0.57
     to
    0.56
     pentru
    0.51
     neke
    0.49
    தெ
    0.49
     برای
    0.49
    для
    0.49
    untuk
    0.48
     để
    0.48
    Act Density 0.002%

    No Known Activations