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

    Neuronpedia

    INDEX
    Explanations

    running away

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     постепен
    0.42
     DOA
    0.38
     ओवरटाइम
    0.38
    મિત
    0.37
    酞
    0.37
    有意
    0.37
     thăm
    0.37
    Enfin
    0.37
    鿢
    0.37
    িয়াস
    0.36
    POSITIVE LOGITS
     away
    0.89
    away
    0.78
     Away
    0.70
    Away
    0.66
     AWAY
    0.65
     downhill
    0.54
     rushing
    0.54
    🏃
    0.53
    奔
    0.52
     flee
    0.51
    Act Density 0.008%

    No Known Activations