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

    Neuronpedia

    INDEX
    Explanations

    animal behaviors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     говоря
    0.47
    纰
    0.42
    斩
    0.42
     കൈ
    0.40
    谈
    0.40
     codecs
    0.40
     deliverables
    0.39
     ล้าน
    0.38
     handcuffed
    0.38
     vállalat
    0.38
    POSITIVE LOGITS
     foraging
    0.86
     snout
    0.77
     burrow
    0.75
     territorial
    0.73
     sniffing
    0.71
     forage
    0.69
     paws
    0.68
     licking
    0.68
     paw
    0.65
    叼
    0.65
    Act Density 0.109%

    No Known Activations