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

    Neuronpedia

    INDEX
    Explanations

    related memory connections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     shores
    0.42
     coast
    0.41
     coastline
    0.41
     coasts
    0.39
     తెలిసి
    0.38
     পাঁ
    0.38
    रांत
    0.38
     côtes
    0.38
     неравен
    0.37
    海岸
    0.36
    POSITIVE LOGITS
     RELATED
    0.73
     related
    0.70
     Related
    0.70
    Related
    0.70
    related
    0.68
    RELATED
    0.57
     terkait
    0.55
    相关
    0.54
    相關
    0.54
    xa
    0.50
    Act Density 0.001%

    No Known Activations