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

    Neuronpedia

    INDEX
    Explanations

    collective nouns for animals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     flock
    0.57
     herd
    0.54
    herd
    0.53
     swarm
    0.52
     horde
    0.49
     群
    0.46
    群
    0.46
    Herd
    0.45
    群体
    0.43
     hordes
    0.42
    POSITIVE LOGITS
     murders
    0.50
     murder
    0.46
     bachelor
    0.46
     Murder
    0.45
    Murder
    0.45
    murder
    0.44
     cyn
    0.43
    noisy
    0.42
    congress
    0.41
     congress
    0.40
    Act Density 0.006%

    No Known Activations