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

    Neuronpedia

    INDEX
    Explanations

    completion or reaching a state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inmediata
    0.38
     ऊंची
    0.38
     মন
    0.38
     inmediato
    0.37
     immediatamente
    0.37
     hemen
    0.36
     instantly
    0.36
                      
    0.35
     imediat
    0.35
     immediately
    0.35
    POSITIVE LOGITS
     reached
    1.59
     reach
    1.52
     reaches
    1.41
    reached
    1.40
    到了
    1.37
    reach
    1.34
     reaching
    1.29
    到達
    1.27
    Reach
    1.26
    Reached
    1.26
    Act Density 0.011%

    No Known Activations