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

    Neuronpedia

    INDEX
    Explanations

    whales and dolphins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     raise
    0.88
    raise
    0.86
     Raising
    0.86
     raising
    0.85
    Raise
    0.84
     Raise
    0.82
     Soils
    0.81
     raised
    0.78
    raised
    0.78
    Raising
    0.77
    POSITIVE LOGITS
     whales
    2.12
     whale
    2.04
     dolphins
    2.00
     dolphin
    1.89
     Whale
    1.80
    鲸
    1.70
    dolphin
    1.70
    whale
    1.69
     Dolphin
    1.65
     Dolphins
    1.61
    Act Density 0.188%

    No Known Activations